Countering Malicious DeepFakes: Survey, Battleground, and Horizon
Open accessThe DOI matches its Crossref record; 345 of the 346 references it cites were found in a registry or an index, and 1 are not checked yet; 73 of the 188 sources its claims cite were checked for support.
Abstract
The creation or manipulation of facial appearance through deep generative approaches, known as DeepFake, have achieved significant progress and promoted a wide range of benign and malicious applications, e.g., visual effect assistance in movie and misinformation generation by faking famous persons. The evil side of this new technique poses another popular study, i.e., DeepFake detection aiming to identify the fake faces from the real ones. With the rapid development of the DeepFake-related studies in the community, both sides (i.e., DeepFake generation and detection) have formed the relationship of battleground, pushing the improvements of each other and inspiring new directions, e.g., the evasion of DeepFake detection. Nevertheless, the overview of such battleground and the new direction is unclear and neglected by recent surveys due to the rapid increase of related publications, limiting the in-depth understanding of the tendency and future works. To fill this gap, in this paper, we provide a comprehensive overview and detailed analysis of the research work on the topic of DeepFake generation, DeepFake detection as well as evasion of DeepFake detection, with more than 318 research papers carefully surveyed. We present the taxonomy of various DeepFake generation methods and the categorization of various DeepFake detection methods, and more importantly, we showcase the battleground between the two parties with detailed interactions between the adversaries (DeepFake generation) and the defenders (DeepFake detection). The battleground allows fresh perspective into the latest landscape of the DeepFake research and can provide valuable analysis towards the research challenges and opportunities as well as research trends and future directions. We also elaborately design interactive diagrams (http://www.xujuefei.com/dfsurvey) to allow researchers to explore their own interests on popular DeepFake generators or detectors.
Verified 2026-11-19 · 1 reference not checked yet
Overview
CoChat Summary
TL;DR
This survey reviews more than 318 papers on DeepFake generation, detection, and evasion, framing generation and detection as an adversarial “battleground.” It provides taxonomies, technical-evolution analyses, dataset summaries, and future research directions for countering malicious DeepFakes.
Key findings
- The survey collected 318 papers; about 78% appeared in the last two years, and it tabulates 83 DeepFake generation methods and 117 DeepFake detection methods.
- DeepFake generation is organized into four categories: entire face synthesis, attribute manipulation, identity swap, and expression swap; identity swap ranks highest in detector popularity, while expression swap is least attempted.
- Detection methods are grouped into spatial-based, frequency-based, and biological-signal-based approaches; evasion methods are grouped into adversarial attacks, frequency-domain trace removal, and filtering/generative reconstruction.
- In challenges, DFDC had 2,114 teams; 60% of submissions had log loss ≤ 0.69, and all top-5 solutions were image-based, with three using EfficientNet. DeeperForensics Challenge 2020 had 115 registered participants and 25 valid submissions; two of the top-3 used EfficientNet and all used augmentation.
Methods
- This is a survey/analysis paper, not an experimental study. Papers were collected from a GitHub repository, keyword matching on Google Scholar, DBLP, and arXiv, plus manual browsing of recent top-tier conferences and workshops.
- The analysis includes taxonomies of generation and detection methods, technical-evolution diagrams, Sankey and chord diagrams for method interactions, Elo ratings for generation methods, and detailed tables of real/fake datasets and detection performance.
Limitations
- The paper states it focuses solely on facial DeepFakes; social and ethical aspects are briefly touched but are not the focus of the survey.
- The paper notes an inherent shortcoming of Elo rating: a generation method that appears once but beats high-score competitors can rise sharply, while a method not detected for a long time keeps an unchanged score that may not reflect its true difficulty.
- The text makes evident that DeepFake detection generally lags behind generation, and many detectors lack robustness, generalization, or explainability; the provided text is also truncated, omitting part of the detection and battleground discussion.
Model-written summary of a shortened version of the paper’s full text (it is longer than we read). Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
62 Valid · 31 Not valid · 108 Not checked · 138 Own results and interpretations
At least one cited source doesn’t support this claim or points to a different paper, and none confirmed it — see the verdicts below.
In the paper
“Although effective, IcGAN can be time-consuming when it aims to perform the manipulation of multiple facial attributes since each attribute is addressed via an independent deep model.”
What the sources say
- Disputedcites Perarnau et al. 2016 matched to “Invertible Conditional GANs for image editing” (2016) sourceExperimental — accuracy not yet measured
The paper describes two independent encoders—one for the latent representation z and one for the attribute information y—not a separate deep model for each facial attribute (Section 4.1, p. 3; Section 6, p. 8). It demonstrates edits across 18 CelebA attributes by modifying y (Section 5.4, p. 7). The copy does not assess whether editing multiple attributes is time-consuming, but it contradicts the claimed reason. (LLM, conf=0.86)
Checked by a reasoning model — may be wrong.
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Disputed
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“The CramerGANperformssignificantly better than the WGAN.”
What the sources say
- Partly supportedcites Bellemare et al. 2017 matched to “The Cramer Distance as a Solution to Biased Wasserstein Gradients” (2017) sourceExperimental — accuracy not yet measured
Section 5.1 (p. 7) reports that Cramér GAN produced more stable learning and more diverse samples than WGAN-GP; the experiments on p. 8 give examples of both advantages. The claim overgeneralizes this comparison to WGAN and says “significantly better” without specifying the outcomes or conditions the paper evaluated. (LLM, conf=0.86)
boostedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“according to the surveys (Verdoliva 2020; Nguyen et al. 2019d; Tolosana et al. 2020; Lyu 2020), GANs are the mainstream baseline technique.”
What the sources say
- Partly supportedcites Verdoliva 2020 matched to “Media Forensics and DeepFakes: An Overview” (2020) sourceExperimental — accuracy not yet measured
Section II, “Fake Content Generation” (p. 3), describes GANs as a successful approach to synthesizing complete media assets, especially photorealistic faces. It also names autoencoders; the copy does not establish that GANs are the mainstream or baseline technique for entire-face synthesis. (LLM, conf=0.79)
- Not matchedcites Nguyen et al. 2019d
More than one paper fits this citation.
- Supportedcites Tolosana et al. 2020 matched to “Deepfakes and beyond: A Survey of face manipulation and fake detection” (2020) source
The survey’s “Types of Facial Manipulations” section says entire face synthesis is usually performed through GANs. Its “Manipulation Techniques and Public Databases” section also says the four relevant public databases all use ProGAN or StyleGAN, supporting the characterization of GANs as the mainstream technique for this task. (LLM, conf=0.91)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“Karras et al. (2017) propose to grow both the generator and discriminator progressively and implement the PGGAN, which significantly improves the generation size to at least 1024 × 1024.”
What the sources say
- Supportedcites Karras et al. 2017 matched to “Progressive Growing of GANs for Improved Quality, Stability, and Variation” (2017) source
Section 2 (p. 2) describes progressively growing both the generator and discriminator and shows generated images at 1024 × 1024. Section 6.3 (p. 8) says the approach handles high output resolutions robustly and reports 1024 × 1024 images produced by the network. (LLM, conf=0.91)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“In previous works, the absence of paired examples is always the limitation in image transformation tasks. CycleGAN has artfully solved this problem.”
What the sources say
- Supportedcites Zhu et al. 2017 matched to “Unpaired image-to-image translation using cycle-consistent adversarial networks” (2017) source
The Results section identifies CycleGAN as the authors’ method and says it is applied where paired data does not exist. Section 5.1 reports that it learns image-to-image mappings without paired supervision, supporting the attributed claim. (LLM, conf=0.90)
boostedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
90 more claims · 9 with their cited sources checked
Create a free account to see all 339 claims and to verify the 3 references still open.
- Probably not a substantial claim. 191
- It may state two separate claims as one. 101
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Existing surveys [4], [16] relevant to deepfakes predominantly emphasize deepfake generation or general synthetic media detection, whereas our survey is exclusively tailored to the detection of facial deepfakes.”
From Evolving from Single-modal to Multi-modal Facial Deepfake Detection: Progress and Challenges (2024) · cites this paper as [16]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Earlier surveys [16], [17], [18], [19] predominantly address research published up to 2023, missing significant advancements in recent years.”
From Evolving from Single-modal to Multi-modal Facial Deepfake Detection: Progress and Challenges (2024) · cites this paper as [16]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“While previous surveys [4], [16], [17] limit their discussions primarily to visual manipulations, we systematically explore recent developments in detecting multi-modal forgeries that simultaneously involve audio, visual, and textual modalities.”
From Evolving from Single-modal to Multi-modal Facial Deepfake Detection: Progress and Challenges (2024) · cites this paper as [16]
The cited source says what the claim attributes to it.
In the citing paper
“FF++ [57] is one of the most popular datasets [22], but it contains limited types of deepfake data.”
From DEEPFAKER: A Unified Evaluation Platform for Facial Deepfake and Detection Models (2024) · cites this paper as [22]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ 3.7 Fake Dataset
“The DFDC is a publicly-available face swap video dataset, with 128,514 videos, over 100,000 total clips sourced from 3426 actors.”
§ 3.9 Summary of DeepFake Generation Methods
“| DFDC (Dolhansky et al. 2020) | 128,154 | - | - | 23,954 | 104,500 |”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ 3.6 Real Dataset
“MegaFace(Kemelmacher-Shlizermanetal.2016)includes more than 690K different individuals with one million photos.”
§ 3.9 Summary of DeepFake Generation Methods
“| MegaFace (Kemelmacher-Shlizerman et al. 2016) | 690,572 | 4,700,000 | 6.81 |”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ 2.3 Paper Collection Results
“One fourth of the papers are published in top conferences”
§ 2.3 Paper Collection Results
“Half of the papers are published in top conferences.”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ 2.1 Survey Scope
“CVPR, which accounts for about half the published top papers.”
§ 2.3 Paper Collection Results
“CVPR, which accounts for about two-thirds the published top papers.”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
“The DeepFake-TIMIT dataset (Korshunov and Marcel 2018) consists of 620 DeepFake videos of 32 subjects. In DeepFake-TIMIT, each subject has 20 DeepFake videos.”
Reported 620 · recomputed 640
3 more findings
Create a free account to see every finding of this check.
Citations
Cites
Items 201–346 of 346
Predicting Heart Rate Variations of Deepfake Videos using Neural ODE
Fernandes, S., Raj, S., Ortiz, E., Vintila, I., Salter, M., Urosevic, G., & Jha, S. (2019) · 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) · doi:10.1109/iccvw.2019.00213 · Cited by 129 · cited 1×
“Fernandes et al. (2019) use neural ordinary differential equation (Neural-ODE) (Chen et al., 2018b) trained on the original videos to predict the heart rate of testing videos.”
MethodExposing GAN-synthesized Faces Using Landmark Locations
Yang, X., Li, Y., Qi, H., & Lyu, S. (2019) · Proceedings of the ACM Workshop on Information Hiding and Multimedia Security · doi:10.1145/3335203.3335724 · Cited by 124 · cited 3×
“Early works study the irregular eye blinking (Li et al., 2018b), the mismatch facial landmarks (Yang et al., 2019a,b), and the fixed size of synthesized faces (Li and Lyu, 2019), etc .”
BackgroundMethodInformation Bottleneck Disentanglement for Identity Swapping
Gao, G., Huang, H., Fu, C., Li, Z., & He, R. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00341 · Cited by 123 · cited 9×
“To solve this problem, Gao et al. (2021d) propose high-fidelity arbitrary face editing (HifaFace) to maintain rich details of undesired attribute areas.”
BackgroundMethodInfluentialUse of a Capsule Network to Detect Fake Images and Videos
Nguyen, H. H., Yamagishi, J., & Echizen, I. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.12467 · Cited by 121 · cited 5×
“In addition, there are also a few relatable DeepFake surveys first published in late 2019 and early 2020 (Nguyen et al., 2019d; Tolosana et al., 2020; Lyu, 2020).”
BackgroundMethodInfluentialGauGAN: semantic image synthesis with spatially adaptive normalization
Park, T., Liu, M.-Y., Wang, T.-C., & Zhu, J.-Y. (2019) · ACM SIGGRAPH 2019 Real-Time Live! · doi:10.1145/3306305.3332370 · Cited by 121
FReTAL: Generalizing Deepfake Detection using Knowledge Distillation and Representation Learning
Kim, M., Tariq, S., & Woo, S. S. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw53098.2021.00111 · Cited by 118
Adversarial Threats to DeepFake Detection: A Practical Perspective
Neekhara, P., Dolhansky, B., Bitton, J., & Ferrer, C. C. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw53098.2021.00103 · Cited by 117 · cited 2×
“Neekhara et al. (2021) further study the adversarial attack-based evasion methods on the more challenging DeepFake Detection Challenge (DFDC) dataset (Wikipedia, 2021a).”
BackgroundMethodCiftci, U. A., Demir, I., & Yin, L. (2020) · 2020 IEEE International Joint Conference on Biometrics (IJCB) · doi:10.1109/ijcb48548.2020.9304909 · Cited by 115 · cited 3×
“FakeCatcher (Ciftci et al., 2020a) has collected over 140 online videos, up to 30GB. Unlike most of the fake datasets, it includes “in the wild” videos, independent of the generative model, resolution, compression, content, and context. iFakeFaceDB (Neves et al., 2020) is a fake image dataset for…”
BackgroundMethodInterpretable and Trustworthy Deepfake Detection via Dynamic Prototypes
Trinh, L., Tsang, M., Rambhatla, S., & Liu, Y. (2021) · 2021 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv48630.2021.00202 · Cited by 115 · cited 2×
“DPNet (Trinh et al., 2021) captures the temporal dynamic features with a carefully”
BackgroundSelf-citationFace image manipulation detection based on a convolutional neural network
Dang, L. M., Hassan, S. I., Im, S., & Moon, H. (2019) · Expert Systems with Applications · doi:10.1016/j.eswa.2019.04.005 · Cited by 114 · cited 23×
“P represents the method simply employs peer works for comparison, T indicates the method simply adopts some simple CNN models for comparison, B denotes the method leverages both peer works and conventional CNN models for comparison.”
BackgroundInfluentialTowards Generalizable Deepfake Detection with Locality-aware AutoEncoder
Du, M., Pentyala, S., Li, Y., & Hu, X. (2020) · Proceedings of the 29th ACM International Conference on Information & Knowledge Management · doi:10.1145/3340531.3411892 · Cited by 114
Deep learning for deepfakes creation and detection: a survey
Nguyen, T. T., Nguyen, Q. V. H., Nguyen, D. T., Nguyen, D. T., Huynh-The, T., Nahavandi, S., Nguyen, T. T., Pham, Q.-V., & Nguyen, C. M. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4030341 · Cited by 112
Fraga-Lamas, P., & Fernandez-Carames, T. M. (2020) · IT Professional · doi:10.1109/mitp.2020.2977589 · Cited by 111 · cited 1×
“Fraga-Lamas and Fernández-Caramés (2020) provide a comprehensive overview by leveraging distributed ledger technologies (DLT) to combat digital deception.”
BackgroundFace Forgery Detection by 3D Decomposition
Zhu, X., Wang, H., Fei, H., Lei, Z., & Li, S. Z. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00295 · Cited by 106
Learning a Facial Expression Embedding Disentangled from Identity
Zhang, W., Ji, X., Chen, K., Ding, Y., & Fan, C. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.00669 · Cited by 104
CNN Detection of GAN-Generated Face Images based on Cross-Band Co-occurrences Analysis
Barni, M., Kallas, K., Nowroozi, E., & Tondi, B. (2020) · 2020 IEEE International Workshop on Information Forensics and Security (WIFS) · doi:10.1109/wifs49906.2020.9360905 · Cited by 103 · cited 2×
“Barni et al. (2020) propose exploiting the inconsistencies among spectral bands, then a CNN model is trained with cross-band co-occurrence matrices and pixel co-occurrence matrices for discriminating real and fake faces.”
BackgroundFakeLocator: Robust Localization of GAN-Based Face Manipulations
Huang, Y., Juefei-Xu, F., Guo, Q., Liu, Y., & Pu, G. (2022) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2022.3141262 · Cited by 102
Self-citationLe, T.-N., Nguyen, H. H., Yamagishi, J., & Echizen, I. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00996 · Cited by 97 · cited 5×
“Furthermore, OpenForensics can also be used for general object detection and segmentation tasks, which shows its versatility.”
BackgroundMethodInfluentialSSTNet: Detecting Manipulated Faces Through Spatial, Steganalysis and Temporal Features
Wu, X., Xie, Z., Gao, Y., & Xiao, Y. (2020) · ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp40776.2020.9053969 · Cited by 94 · cited 2×
“SSTNet (Wu et al., 2020) incorporates the spatial, steganalysis, and temporal features for detecting DeepFakes.”
MethodDiverse Image Synthesis From Semantic Layouts via Conditional IMLE
Li, K., Zhang, T., & Malik, J. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00432 · Cited by 91 · cited 1×
“Formulating fake forensics as a segmentation task to localize the manipulated region in synthesized faces is another interesting idea in fighting against DeepFakes (Li et al., 2019a; Chen and Yang, 2020).”
BackgroundA Closer Look at Fourier Spectrum Discrepancies for CNN-generated Images Detection
Chandrasegaran, K., Tran, N.-T., & Cheung, N.-M. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00712 · Cited by 90
(2018) · Neural Information Processing Systems · Cited by 89
High-Fidelity and Arbitrary Face Editing
Gao, Y., Wei, F., Bao, J., Gu, S., Chen, D., Wen, F., & Lian, Z. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01585 · Cited by 89 · cited 9×
“To solve this problem, Gao et al. (2021d) propose high-fidelity arbitrary face editing (HifaFace) to maintain rich details of undesired attribute areas.”
BackgroundMethodInfluentialICface: Interpretable and Controllable Face Reenactment Using GANs
Tripathy, S., Kannala, J., & Rahtu, E. (2020) · 2020 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv45572.2020.9093474 · Cited by 88 · cited 7×
“To solve these problems, ICFA (Tripathy et al., 2020) proposes to use action units (AUs) (Friesen and Ekman, 1978) to represent the emotions.”
BackgroundMethodInfluentialTraining Strategies and Data Augmentations in CNN-based DeepFake Video Detection
Bondi, L., Daniele Cannas, E., Bestagini, P., & Tubaro, S. (2020) · 2020 IEEE International Workshop on Information Forensics and Security (WIFS) · doi:10.1109/wifs49906.2020.9360901 · Cited by 86
DeepFaceLab: Integrated, flexible and extensible face-swapping framework
Perov, I., Gao, D., Chervoniy, N., Liu, K., Marangonda, S., Umé, C., Dpfks, Facenheim, C. S., RP, L., Jiang, J., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.05535 · Cited by 86
Photographic Image Synthesis with Cascaded Refinement NetworksPreprint
Chen, Q., & Koltun, V. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1707.09405 · Cited by 79
Homomorphic Latent Space Interpolation for Unpaired Image-To-Image Translation
Chen, Y.-C., Xu, X., Tian, Z., & Jia, J. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.00251 · Cited by 78 · cited 2×
“Octave convolution (OctConv) (Chen et al., 2019b) is leveraged for capturing the frequency domain to learn the intrinsic feature from CDI and SI to determine fake faces.”
BackgroundMethodSpatio-temporal Features for Generalized Detection of Deepfake VideosPreprint
Ganiyusufoglu, I., Ngo, M., Savov, N., Karaoğlu, S., & Gevers, T. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.11844 · Cited by 76
Juefei-Xu, F., Luu, K., & Savvides, M. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2468173 · Cited by 74 · cited 2×
“, 2022) where only the eye region is visible (Juefei-Xu and Savvides, 2016; Juefei-Xu et al., 2015), heavy makeups, heavy facial hairs, etc.”
BackgroundSelf-citationOn the use of Benford's law to detect GAN-generated images
Bonettini, N., Bestagini, P., Milani, S., & Tubaro, S. (2021) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr48806.2021.9412944 · Cited by 74
Learning to Adversarially Blur Visual Object Tracking
Guo, Q., Cheng, Z., Juefei-Xu, F., Ma, L., Xie, X., Liu, Y., & Zhao, J. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01066 · Cited by 73 · cited 2×
“For example, Guo et al. (2020a) realize an adversarial blur attack that can generate realistic-blurred images and mislead the state-of-the-art deep neural networks (Guo et al., 2021).”
BackgroundSelf-citationSwapped face detection using deep learning and subjective assessment
Ding, X., Raziei, Z., Larson, E. C., Olinick, E. V., Krueger, P., & Hahsler, M. (2020) · EURASIP Journal on Information Security · doi:10.1186/s13635-020-00109-8 · Cited by 71 · cited 1×
“…of deep learning, various DNN-based approaches are continuously proposed for distinguishing synthesized fake faces, such as deep transfer learning (Ding et al., 2020; Dogonadze et al., 2020; Jeon et al., 2020a), customized CNN (Dang et al., 2019; Marra et al., 2020; Coz-zolino et al., 2018), CNN…”
BackgroundFakePolisher: Making DeepFakes More Detection-Evasive by Shallow Reconstruction
Huang, Y., Juefei-Xu, F., Wang, R., Guo, Q., Ma, L., Xie, X., Li, J., Miao, W., Liu, Y., & Pu, G. (2020) · Proceedings of the 28th ACM International Conference on Multimedia · doi:10.1145/3394171.3413732 · Cited by 71 · cited 7×
“(Huang et al., 2020b).”
BackgroundMethodInfluentialSelf-citationDetecting Face2Face Facial Reenactment in Videos
Kumar, P., Vatsa, M., & Singh, R. (2020) · 2020 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv45572.2020.9093628 · Cited by 68 · cited 2×
“…CNN with image segmentation (Yu et al., 2019a), capsule networks (Nguyen et al., 2019b,c), pairwise learning (Hsu et al., 2020), metric learning (Kumar et al., 2020), incremental learning (Marra et al., 2019b), multiple instance learning (Li et al., 2020d), few-shot learning (Mansourifar and…”
BackgroundMethodDetection of Fake Images Via The Ensemble of Deep Representations from Multi Color Spaces
He, P., Li, H., & Wang, H. (2019) · 2019 IEEE International Conference on Image Processing (ICIP) · doi:10.1109/icip.2019.8803740 · Cited by 67 · cited 11×
“StarGAN (Choi et al., 2018) AttGAN (He et al., 2019b) Apply an attribute classification constraint to the generated image.”
BackgroundMethodInfluentialDetecting Deep-Fake Videos from Aural and Oral Dynamics
Agarwal, S., & Farid, H. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw53098.2021.00109 · Cited by 66
Fdftnet: facing off fake images using fake detection fine-tuning network
Jeon, H., Bang, Y., & Woo, S. S. (2020) · IFIP Advances in Information and Communication Technology · doi:10.1007/978-3-030-58201-2_28 · Cited by 65 · cited 4×
“Due to the significant progress of DNN models in various cutting-edge fields, powerful DNN models are designed or employed for spotting DeepFakes, such as FDFtNet (Jeon et al., 2020b) or ResNet-50 (Wang et al., 2020e).”
BackgroundMethodInfluentialGated-GAN: Adversarial gated networks for multi-collection style transfer
Chen, X., Xu, C., Yang, X., Song, L., & Tao, D. (2019) · UTS ePRESS (University of Technology Sydney) · Cited by 63
Deepfake Detection using Spatiotemporal Convolutional Networks
de Lima, O., Franklin, S., Basu, S., Karwoski, B., & George, A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.14749 · Cited by 62
Detecting GAN generated Fake Images using Co-occurrence MatricesPreprint
Nataraj, L., Mohammed, T. M., Chandrasekaran, S., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.06836 · Cited by 54 · cited 1×
“Others explore utilizing the co-occurrence matrices for differentiating real and fake faces (Nataraj et al., 2019).”
BackgroundFaceInpainter: High Fidelity Face Adaptation to Heterogeneous Domains
Li, J., Li, Z., Cao, J., Song, X., & He, R. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.00505 · Cited by 52 · cited 3×
“FaceInpainter (Li et al., 2021a) proposes a controllable face inpainting network under heterogeneous domains ( i.e ., oil painting, 3D cartoons, pencil drawing, exaggerated drawing, etc .).”
BackgroundFACEGAN: Facial Attribute Controllable rEenactment GAN
Tripathy, S., Kannala, J., & Rahtu, E. (2021) · 2021 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv48630.2021.00137 · Cited by 51
Self-Supervised Sketch-to-Image Synthesis
Liu, B., Zhu, Y., Song, K., & Elgammal, A. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i3.16304 · Cited by 51 · cited 3×
“…et al., 2018c), (Yao et al., 2019), image inpainting (Yu et al., 2018), (Yu et al., 2018), rendering (Chen and Koltun, 2017), (Park et al., 2019), (Liu et al., 2021a), super resolution (Dai et al., 2019), (Guo et al., 2020b), (Liu et al., 2020a), (Mei et al., 2020), fusion (Lin et al., 2019),…”
MethodDeepfake Videos in the Wild: Analysis and Detection
Pu, J., Mangaokar, N., Kelly, L., Bhattacharya, P., Sundaram, K., Javed, M., Wang, B., & Viswanath, B. (2021) · Proceedings of the Web Conference 2021 · doi:10.1145/3442381.3449978 · Cited by 51
Dynamic texture analysis for detecting fake faces in video sequences
Bonomi, M., Pasquini, C., & Boato, G. (2021) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2021.103239 · Cited by 50
Woods, W., Chen, J., & Teuscher, C. (2019) · Nature Machine Intelligence · doi:10.1038/s42256-019-0104-6 · Cited by 48 · cited 2×
“with the Lipschitz regularization (Woods et al., 2019) and deep image prior (Ulyanov et al.”
MethodSSR2: Sparse signal recovery for single-image super-resolution on faces with extreme low resolutions
Abiantun, R., Juefei-Xu, F., Prabhu, U., & Savvides, M. (2019) · Pattern Recognition · doi:10.1016/j.patcog.2019.01.032 · Cited by 47 · cited 1×
“In the real-world, Deep-Fakes can easily suffer from various degradations, such as image/video compression, added Gaussian noises, blurring, low-light (Juefei-Xu and Savvides, 2015), low-resolution (Abiantun et al., 2019), etc .”
BackgroundSelf-citationThe eyes know it: FakeET- An Eye-tracking Database to Understand Deepfake Perception
Gupta, P., Chugh, K., Dhall, A., & Subramanian, R. (2020) · Proceedings of the 2020 International Conference on Multimodal Interaction · doi:10.1145/3382507.3418857 · Cited by 47 · cited 1×
“Instead of a focus on the multimedia self, FakeET (Gupta et al., 2020) explores to leverage the user behavior clues for DeepFake detection, specifically the eye-gaze.”
BackgroundCNN-generated images are surprisingly easy to spot... for nowPreprint
Wang, S.-Y., Wang, O., Zhang, R., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.11035 · Cited by 44
Watch out! Motion is Blurring the Vision of Your Deep Neural Networks
Guo, Q., Juefei-Xu, F., Xie, X., Ma, L., Wang, J., Yu, B., Feng, W., & Liu, Y. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.03500 · Cited by 43
Self-citationDeep Detection for Face Manipulation
Feng, D., Lu, X., & Lin, X. (2020) · Communications in computer and information science · doi:10.1007/978-3-030-63823-8_37 · Cited by 43
Poster: Towards Robust Open-World Detection of Deepfakes
Sohrawardi, S. J., Chintha, A., Thai, B., Seng, S., Hickerson, A., Ptucha, R., & Wright, M. (2019) · Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3319535.3363269 · Cited by 41
Secure Detection of Image Manipulation by Means of Random Feature Selection
Chen, Z., Tondi, B., Li, X., Ni, R., Zhao, Y., & Barni, M. (2019) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2019.2901826 · Cited by 40 · cited 2×
“Octave convolution (OctConv) (Chen et al., 2019b) is leveraged for capturing the frequency domain to learn the intrinsic feature from CDI and SI to determine fake faces.”
BackgroundMethodFinding Facial Forgery Artifacts with Parts-Based Detectors
Schwarcz, S. L., & Chellappa, R. (2021) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw53098.2021.00104 · Cited by 40
Face Manipulation Detection via Auxiliary Supervision
Wang, X., Yao, T., Ding, S., & Ma, L. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-63830-6_27 · Cited by 39 · cited 7×
“W a n g ' 21 2017) with significant accuracy reduction on the public datasets (Wang et al., 2020e; Frank et al., 2020).”
BackgroundMethodInfluentialSelf-citationRSGAN: Face Swapping and Editing using Face and Hair Representation in Latent Spaces
Natsume, R., Yatagawa, T., & Morishima, S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1804.03447 · Cited by 39
Preliminary Forensics Analysis of DeepFake Images
Guarnera, L., Giudice, O., Nastasi, C., & Battiato, S. (2020) · 2020 AEIT International Annual Conference (AEIT) · doi:10.23919/aeit50178.2020.9241108 · Cited by 38 · cited 3×
“Ac-tually, leveraging the frequency domain to distinguish real and fake faces is widely applied in recent studies (Durall et al., 2019; Bonettini et al., 2021a; Guarnera et al., 2020c).”
MethodT-GD: Transferable GAN-generated Images Detection Framework
Jeon, H., Bang, Y., Kim, J., & Woo, S. S. (2020) · arXiv · doi:10.48550/arxiv.2008.04115 · Cited by 38
Bias Field Poses a Threat to DNN-Based X-Ray Recognition
Tian, B., Guo, Q., Juefei-Xu, F., Chan, W. L., Cheng, Y., Li, X., Xie, X., & Qin, S. (2021) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme51207.2021.9428437 · Cited by 37
Self-citationWildDeepfake: A Challenging Real-World Dataset for Deepfake Detection
Zi, B., Chang, M., Chen, J., Ma, X., & Jiang, Y. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.01456 · Cited by 37
AVA: Adversarial Vignetting Attack against Visual Recognition
Tian, B., Juefei-Xu, F., Guo, Q., Xie, X., Li, X., & Liu, Y. (2021) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2021/145 · Cited by 36 · cited 1×
“…proposed for natural degradations like weather elements (Zhai et al., 2022, 2020; Gao et al., 2021b), exposure (Gao et al., 2022, 2020; Cheng et al., 2020), lighting (Gao et al., 2021c; Tian et al., 2021b,a; Sun et al., 2022), shadow (Fu et al., 2021a,b), defocus blur (Huang et al., 2021b), etc .”
BackgroundSelf-citationSecure Detection of Image Manipulation by Means of Random Feature Selection
Chen, Z., Tondi, B., Li, X.-L., Ni, R.-R., Zhao, Y., & Barni, M. (2018) · IEEE Transactions on Information Forensics and Security · doi:10.48550/arxiv.1802.00573 · Cited by 36
AdvHaze: Adversarial Haze AttackPreprint
Gao, R., Guo, Q., Juefei-Xu, F., Yu, H., & Feng, W. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.13673 · Cited by 35
Self-citationTowards Generalizable Forgery Detection with Locality-aware AutoEncoder.Preprint
Du, M., Pentyala, S., Li, Y., & Hu, X. (2019) · arXiv (Cornell University) · Cited by 33
Emotions Don't Lie: An Audio-Visual Deepfake Detection Method Using Affective CuesPreprint
Mittal, T., Bhattacharya, U., Chandra, R., Bera, A., & Manocha, D. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.06711 · Cited by 33
Attentive Semantic Exploring for Manipulated Face Detection
Chen, Z., & Yang, H. (2021) · ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp39728.2021.9414225 · Cited by 32 · cited 2×
“Formulating fake forensics as a segmentation task to localize the manipulated region in synthesized faces is another interesting idea in fighting against DeepFakes (Li et al., 2019a; Chen and Yang, 2020).”
BackgroundMMSys'21 Grand Challenge on Detecting CheapfakesPreprint
Aneja, S., Midoglu, C., Dang‐Nguyen, D., Riegler, M. A., Halvorsen, P., Nießner, M., Adsumilli, B., & Bregler, C. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.05297 · Cited by 31
TediGAN: Text-Guided Diverse Face Image Generation and ManipulationPreprint
Xia, W., Yang, Y., Xue, J., & Wu, B. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.03308 · Cited by 31
Fake Generated Painting Detection Via Frequency Analysis
Bai, Y. S., Guo, Y., Wei, J., Lu, L., Wang, R., & Wang, Y. (2020) · Proceedings - International Conference on Image Processing · doi:10.1109/icip40778.2020.9190892 · Cited by 30 · cited 2×
“FGPD-FA (Bai et al., 2020) extracts three types of features (e.”
BackgroundSelf-citationNoiseScope: Detecting Deepfake Images in a Blind Setting
Pu, J., Mangaokar, N., Wang, B., Reddy, C. K., & Viswanath, B. (2020) · Annual Computer Security Applications Conference · doi:10.1145/3427228.3427285 · Cited by 30
Do GANs leave artificial fingerprints?Preprint
Marra, F., Gragnaniello, D., Verdoliva, L., & Poggi, G. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1812.11842 · Cited by 30
Yu, C.-M., Chang, C.-T., & Ti, Y.-W. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.12184 · Cited by 29 · cited 3×
“Yu et al. (2019b) first introduce the GAN fingerprints for classifying the images as real or synthesized with GANs.”
BackgroundMethodFocal Frequency Loss for Image Reconstruction and SynthesisPreprint
Jiang, L., Dai, B., Wu, W., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.12821 · Cited by 29
Detection, Attribution and Localization of GAN Generated Images
Goebel, M., Nataraj, L., Nanjundaswamy, T., Mohammed, T. M., Chandrasekaran, S., & Manjunath, B. S. (2021) · Electronic Imaging · doi:10.2352/issn.2470-1173.2021.4.mwsf-276 · Cited by 28
Can Forensic Detectors Identify GAN Generated Images?
Li, H., Chen, H., Li, B., & Tan, S. (2018) · 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.23919/apsipa.2018.8659461 · Cited by 27 · cited 3×
“The UADFV dataset (Li et al., 2018b) consists of 98 videos, with 49 real videos from YouTube and 49 synthesized videos, which are made using the FakeAPP (FaceApp, 2021).”
BackgroundMethodDeepFake Detection Based on the Discrepancy Between the Face and its Context
Nirkin, Y., Wolf, L., Keller, Y., & Hassner, T. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.12262 · Cited by 27
Video Face Manipulation Detection Through Ensemble of CNNs
Bonettini, N., Cannas, E. D., Mandelli, S., Bondi, L., Bestagini, P., & Tubaro, S. (2021) · 2020 25th International Conference on Pattern Recognition (ICPR) · doi:10.1109/icpr48806.2021.9412711 · Cited by 27 · cited 5×
“A recurrent convolutional network is exploited to capture the temporal discrepancies in fake videos (Sabir et al., 2019). de Lima et al. (2020) have employed the temporal information by leveraging various typical CNNs for DeepFake detection.”
BackgroundInfluentialDurall, R., Keuper, M., & Keuper, J. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00791 · Cited by 26 · cited 2×
“WUCGAN (Durall et al., 2020) has shown common up-sampling methods are causing the inability of GANs to reproduce spectral distributions of real images correctly.”
BackgroundIdentity-Driven DeepFake Detection
Dong, X., Bao, J., Chen, D., Zhang, W., Yu, N., Chen, D., Wen, F., & Guo, B. (2020) · arXiv · doi:10.48550/arxiv.2012.03930 · Cited by 26 · cited 2×
“Dong et al. (2020) have built a large-scale DeepFake detection dataset “Vox-DeepFake”, which has a total of 2 million real videos and fake videos.”
BackgroundCan You Spot the Chameleon? Adversarially Camouflaging Images from Co-Salient Object Detection
Gao, R., Guo, Q., Juefei-Xu, F., Yu, H., Fu, H., Feng, W., Liu, Y., & Wang, S. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.00219 · Cited by 25 · cited 1×
“Similar works are proposed for natural degradations like weather elements (Zhai et al., 2022, 2020; Gao et al., 2021b), exposure (Gao et al., 2022, 2020; Cheng et al., 2020), lighting (Gao et al., 2021c; Tian et al., 2021b,a; Sun et al., 2022), shadow (Fu et al., 2021a,b), defocus blur (Huang et…”
BackgroundSelf-citationResponsible Disclosure of Generative Models Using Scalable Fingerprinting
Yu, N., Skripniuk, V., Chen, D., Davis, L. S., & Fritz, M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.08726 · Cited by 24
Complement Face Forensic Detection and Localization with FacialLandmarks
Songsri-in, K., & Zafeiriou, S. P. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.05455 · Cited by 23 · cited 1×
“Songsri-in and Zafeiriou (2019) release the first forensic localization dataset with labeled corresponding binary masks.”
BackgroundSpectral Distribution Aware Image Generation
Jung, S., & Keuper, M. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i2.16267 · Cited by 23 · cited 2×
“Jung and Keuper (2020) identify a straightforward solution for this issue by equipping the generative models with a spectral discrimi-nator, thus the new trained GANs can generate images with realistic frequency spectra.”
BackgroundMethodOne-Shot Free-View Neural Talking-Head Synthesis for Video ConferencingPreprint
Wang, T.-C., Mallya, A., & Liu, M.-Y. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.15126 · Cited by 22
Extracting Deep Local Features to Detect Manipulated Images of Human Faces
Tarasiou, M., & Zafeiriou, S. (2020) · 2020 IEEE International Conference on Image Processing (ICIP) · doi:10.1109/icip40778.2020.9190714 · Cited by 21 · cited 2×
“, 2018), CNN with local features (Tarasiou and Zafeiriou, 2020), CNN with optical flow (Amerini et al.”
BackgroundDeeperForensics Challenge 2020 on Real-World Face Forgery Detection: Methods and ResultsPreprint
Jiang, L., Guo, Z., Wu, W., Liu, Z., Liu, Z., Loy, C. C., Yang, S., Xiong, Y., Xia, W., Chen, B., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.09471 · Cited by 21
AOT: Appearance Optimal Transport Based Identity Swapping for Forgery Detection
Zhu, H., Fu, C., Wu, Q., Wu, W., Qian, C., & He, R. (2020) · arXiv · doi:10.48550/arxiv.2011.02674 · Cited by 20 · cited 2×
“Appearance optimal transport (AOT) (Zhu et al., 2020) has formulated appearance mapping as an optimal transport problem.”
BackgroundTowards Untrusted Social Video Verification to Combat Deepfakes via Face Geometry Consistency
Tursman, E., George, M., Kamara, S., & Tompkin, J. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw50498.2020.00335 · Cited by 19
Fastfood dictionary learning for periocular-based full face hallucination
Juefei-Xu, F., & Savvides, M. (2016) · 2016 IEEE 8th International Conference on Biometrics Theory, Applications and Systems (BTAS) · doi:10.1109/btas.2016.7791174 · Cited by 19 · cited 2×
“, 2022) where only the eye region is visible (Juefei-Xu and Savvides, 2016; Juefei-Xu et al., 2015), heavy makeups, heavy facial hairs, etc.”
BackgroundSelf-citationZooming into Face Forensics: A Pixel-level AnalysisPreprint
Li, J., Shen, T., Zhang, W., Ren, H., Zeng, D., & Mei, T. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.05790 · Cited by 19
(2020) · doi:10.1109/cvprw50498.2020.00329 · Cited by 18 · cited 2×
“However, they are not robust to be deployed in dealing with realworld scenarios according to a recent study (Hulzebosch et al., 2020).”
BackgroundDetecting CNN-Generated Facial Images in Real-World Scenarios
Hulzebosch, N., Ibrahimi, S., & Worring, M. (2020) · arXiv · doi:10.48550/arxiv.2005.05632 · Cited by 18
Exposing Deep-faked Videos by Anomalous Co-motion Pattern Detection
Wang, G., Zhou, J., & Wu, Y. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.04848 · Cited by 17 · cited 7×
“W a n g ' 21 2017) with significant accuracy reduction on the public datasets (Wang et al., 2020e; Frank et al., 2020).”
BackgroundMethodInfluentialSelf-Supervised Video GANs: Learning for Appearance Consistency and Motion Coherency
Hyun, S., Kim, J., & Heo, J.-P. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01068 · Cited by 16 · cited 6×
“For the expression swap, we think the improvements of the diversity of input sources, controllable expression, and video consistency are the major technical characteristics that have been evolved throughout the years, and we highlight seminal works A2V, ICface, SVGAN in the bottom right panel of Figure 5, showcasing t…”
BackgroundInfluentialDeepTag: Robust Image Tagging for DeepFake ProvenancePreprint
Wang, R., Juefei-Xu, F., Guo, Q., Huang, Y., Ma, L., Liu, Y., & Wang, L. (2020) · arXiv (Cornell University) · Cited by 16
Self-citationDetecting Deepfake Videos: An Analysis of Three Techniques
Pishori, A., Rollins, B., van Houten, N., Chatwani, N., & Uraimov, O. (2020) · arXiv · doi:10.48550/arxiv.2007.08517 · Cited by 16
Emotions Don't Lie: A Deepfake Detection Method using Audio-Visual Affective Cues
Mittal, T., Bhattacharya, U., Chandra, R., Bera, A., & Manocha, D. (2020) · Cited by 15
Making Images Undiscoverable from Co-Saliency Detection.Preprint
Gao, R., Guo, Q., Juefei-Xu, F., et al. (2020) · arXiv (Cornell University) · Cited by 15
Self-citationA Convolutional LSTM based Residual Network for Deepfake Video Detection
Tariq, S., Lee, S., & Woo, S. S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.07480 · Cited by 14 · cited 2×
“CLRNet (Tariq et al., 2020) proposes a convolutional long short-term memory (LSTM) based residual network for capturing the temporal information in consecutive frames.”
BackgroundJuefei-Xu, F., & Savvides, M. (2015) · IEEE International Conference on Biometrics: Theory, Applications and Systems (BTAS) · doi:10.1109/btas.2015.7358787 · Cited by 14 · cited 2×
“In the real-world, Deep-Fakes can easily suffer from various degradations, such as image/video compression, added Gaussian noises, blurring, low-light (Juefei-Xu and Savvides, 2015), low-resolution (Abiantun et al., 2019), etc .”
BackgroundSelf-citationCost Sensitive Optimization of Deepfake DetectorPreprint
Kukanov, I., Karttunen, J. P., Sillanpää, H., & Hautamäki, V. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.04199 · Cited by 14
Self-labeled Conditional GANsPreprint
Noroozi, M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.02162 · Cited by 13
CycleGAN without checkerboard artifacts for counter-forensics of fake-image detection
Osakabe, T., Tanaka, M., Kinoshita, Y., & Kiya, H. (2021) · International Workshop on Advanced Imaging Technology (IWAIT) 2021 · doi:10.1117/12.2590977 · Cited by 13
Focal Frequency Loss for Generative ModelsPreprint
Jiang, L., Dai, B., Wu, W., & Loy, C. C. (2020) · arXiv (Cornell University) · Cited by 13
Exploiting Human Social Cognition for the Detection of Fake and Fraudulent Faces via Memory NetworksPreprint
Fernando, T., Fookes, C., Denman, S., & Sridharan, S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.07844 · Cited by 13
GANprintR: Improved Fakes and Evaluation of the State of the Art in Face Manipulation Detection
Neves, J. C., Tolosana, R., Vera-Rodriguez, R., Lopes, V., Proenca, H., & Fierrez, J. (2020) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2020.3007250 · Cited by 12 · cited 7×
“Tolosana et al. (2020) explore the role of different facial regions in contributing to the DeepFake detection.”
BackgroundMethodInfluentialTowards Generalizable Deepfake Detection with Locality-aware AutoEncoderPreprint
Du, M., Pentyala, S., Li, Y., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.05999 · Cited by 12
Detection, Attribution and Localization of GAN Generated ImagesPreprint
Goebel, M. G., Nataraj, L., Nanjundaswamy, T., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.10466 · Cited by 11
Learning to Recognize Patch-Wise Consistency for Deepfake Detection.Preprint
Zhao, T., Xu, X., Xu, M., Ding, H., Xiong, Y., & Xia, W. (2020) · arXiv (Cornell University) · Cited by 11
Fake Face Detection via Adaptive Residuals Extraction NetworkPreprint
Guo, Z., Yang, G., Chen, J., & Sun, X. (2020) · arXiv (Cornell University) · Cited by 10
One-Shot GAN Generated Fake Face DetectionPreprint
Mansourifar, H., & Shi, W. L. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.12244 · Cited by 10 · cited 2×
“…metric learning (Kumar et al., 2020), incremental learning (Marra et al., 2019b), multiple instance learning (Li et al., 2020d), few-shot learning (Mansourifar and Shi, 2020), enhanced MesoNet (Kawa and Syga, 2020; Afchar et al., 2018), a combination with CNN and RNN (Güera and Delp, 2018; Mas…”
BackgroundA Note on Deepfake Detection with Low-Resources
Kawa, P., & Syga, P. (2020) · arXiv · doi:10.48550/arxiv.2006.05183 · Cited by 10 · cited 3×
“…learning (Marra et al., 2019b), multiple instance learning (Li et al., 2020d), few-shot learning (Mansourifar and Shi, 2020), enhanced MesoNet (Kawa and Syga, 2020; Afchar et al., 2018), a combination with CNN and RNN (Güera and Delp, 2018; Mas Montserrat et al., 2020), DNN with contrastive…”
BackgroundInvestigating the Impact of Pre-processing and Prediction Aggregation on the DeepFake Detection Task
Charitidis, P., Kordopatis-Zilos, G., Papadopoulos, S., & Kompatsiaris, I. Y. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.07084 · Cited by 10
FakeTagger: Robust Safeguards against DeepFake Dissemination via Provenance TrackingPreprint
Wang, R., Juefei-Xu, F., Luo, M., Liu, Y., & Wang, L. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.09869 · Cited by 10
Self-citationÇiftçi, U. A., Demir, İ., & Yin, L. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.11363 · Cited by 10
Adversarial Rain Attack and Defensive Deraining for DNN PerceptionPreprint
Zhai, L., Juefei-Xu, F., Guo, Q., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.09205 · Cited by 10
Self-citationMining Generalized Features for Detecting AI-Manipulated Fake FacesPreprint
Yu, Y., Ni, R., & Zhao, Y. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.14129 · Cited by 9
Deep Face Forgery DetectionPreprint
Dogonadze, N., Obernosterer, J., & Hou, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.11804 · Cited by 8 · cited 2×
“…various DNN-based approaches are continuously proposed for distinguishing synthesized fake faces, such as deep transfer learning (Ding et al., 2020; Dogonadze et al., 2020; Jeon et al., 2020a), customized CNN (Dang et al., 2019; Marra et al., 2020; Coz-zolino et al., 2018), CNN with local features…”
BackgroundKoDF: A Large-scale Korean DeepFake Detection DatasetPreprint
Kwon, P., You, J., Nam, G., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.10094 · Cited by 8
Fake face detection via adaptive manipulation traces extraction networkPreprint
Guo, Z., Yang, G., Chen, J., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.04945 · Cited by 7
Interpretable Deepfake Detection via Dynamic Prototypes.Preprint
Trinh, L., Tsang, M. Y. C., Rambhatla, S., & Liu, Y. (2020) · arXiv (Cornell University) · Cited by 6
Self-citationCan You Spot the Chameleon? Adversarially Camouflaging Images from Co-Salient Object DetectionPreprint
Gao, R., Guo, Q., Juefei-Xu, F., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.09258 · Cited by 6
Self-citationBenchmarking Shadow Removal for Facial Landmark Detection and BeyondPreprint
Fu, L., Guo, Q., Juefei-Xu, F., Yu, H., Feng, W., Liu, Y., & Wang, S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.13790 · Cited by 6
Self-citationOne Shot Face Swapping on MegapixelsPreprint
Zhu, Y., Li, Q., Wang, J., Xu, C., & Sun, Z. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.04932 · Cited by 6
Bias Field Poses a Threat to DNN-based X-Ray RecognitionPreprint
Tian, B., Guo, Q., Juefei-Xu, F., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.09247 · Cited by 5
Self-citationDetecting Forged Facial Videos using convolutional neural networkPreprint
Sambhu, N., & Canavan, S. J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.08344 · Cited by 5
The eyes know it: FakeET -- An Eye-tracking Database to Understand Deepfake PerceptionPreprint
Gupta, P., Chugh, K., Dhall, A., & Subramanian, R. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.06961 · Cited by 5
Adversarial Relighting Against Face RecognitionPreprint
Zhang, Q., Guo, Q., Gao, R., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2108.07920 · Cited by 4
Self-citationFinding Facial Forgery Artifacts with Parts-Based DetectorsPreprint
Schwarcz, S. L., & Chellappa, R. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.10688 · Cited by 4
Zhu, J., Guo, Q., Juefei-Xu, F., Huang, Y., Liu, Y., & Pu, G. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-25056-9_24 · Cited by 3 · cited 2×
“In addition, the SOTA detectors may fall short when faces are under occlusions such as facial masks (Zhu et al., 2022) where only the eye region is visible (Juefei-Xu and Savvides, 2016; Juefei-Xu et al., 2015), heavy makeups, heavy facial hairs, etc .”
BackgroundSelf-citationDodging DeepFake Detection via Implicit Spatial-Domain Notch FilteringPreprint
Huang, Y., Juefei-Xu, F., Guo, Q., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.09213 · Cited by 3
Self-citationZhu, J., Guo, Q., Juefei-Xu, F., Huang, Y., Liu, Y., & Pu, G. (2022) · arXiv · doi:10.48550/arxiv.2201.06427 · Cited by 3
Self-citationHomomorphic Interpolation Network for Unpaired Image-to-image Translation
Chen, Y.-C., & Jia, J. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.3036543 · Cited by 2
Self-Supervised Sketch-to-Image SynthesisPreprint
Liu, B., Zhu, Y., Song, K., & Elgammal, A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.09290 · Cited by 1
ALA: Naturalness-aware Adversarial Lightness AttackPreprint
Huang, Y., Sun, L., Guo, Q., et al. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2201.06070
Self-citationIdentifying Invariant Texture Violation for Robust Deepfake Detection
Sun, X., Wu, B., & Chen, W. (2020) · arXiv · doi:10.48550/arxiv.2012.10580 · cited 1×
“Self-supervised learning, free of labels, enables continuous life-long learning on an infinite and smoothly changing data stream (Sun et al., 2020b).”
BackgroundDeepFakesON-Phys: DeepFakes Detection based on Heart Rate Estimation
Hernandez-Ortega, J., Tolosana, R., Fierrez, J., & Morales, A. (2020) · arXiv · doi:10.48550/arxiv.2010.00400
Adversarial Exposure Attack on Diabetic Retinopathy Imagery Grading
Cheng, Y., Guo, Q., Juefei-Xu, F., et al. (2020) · arXiv · doi:10.48550/arxiv.2009.09231
Self-citationNatural & Adversarial Bokeh Rendering via Circle-of-Confusion Predictive Network
Huang, Y., Juefei-Xu, F., Guo, Q., et al. (2021) · arXiv · doi:10.48550/arxiv.2111.12971
Self-citationSpectral Distribution Aware Image Generation
Jung, S., & Keuper, M. (2020) · arXiv · doi:10.48550/arxiv.2012.03110
An Introduction to Variational Autoencoders
Kingma, D. P., & Welling, M. (2019) · arXiv · doi:10.48550/arxiv.1906.02691
Learning Self-Consistency for Deepfake Detection
Zhao, T., Xu, X., Xu, M., et al. (2020) · arXiv · doi:10.48550/arxiv.2012.09311
Le, T.-N., Nguyen, H. H., Yamagishi, J., et al. (2021) · arXiv · doi:10.48550/arxiv.2107.14480
Dynamic texture analysis for detecting fake faces in video sequences
Bonomi, M., Pasquini, C., & Boato, G. (2020) · arXiv · doi:10.48550/arxiv.2007.15271
ID-Reveal: Identity-aware DeepFake Video Detection
Cozzolino, D., Rössler, A., Thies, J., et al. (2020) · arXiv · doi:10.48550/arxiv.2012.02512
Research works printed but not linked: 8
- Chen, Z., & Yang, H. (2021). Attentive semantic exploring for manipulated face detection. ICASSP 2021-2021 IEEE international conference on acoustics (pp. 1985-1989). IEEE: Speech and Signal Processing (ICASSP). · DOI · Paper page
- Frank, J., Eisenhofer, T., Schönherr, L., Fischer, A., Kolossa, D., & Holz,T.(2020).Leveragingfrequencyanalysisfordeepfakeimage recognition. In International conference on machine learning (pp. 3247-3258). PMLR.
- Friesen, E., & Ekman, P. (1978). Facial action coding system: A technique for the measurement of facial movement. Palo Alto, 3 (2), 5.
- Huang, Y., Juefei-Xu, F., Guo, Q., Ma, L., Xie, X., Miao, W., Liu, Y., & Pu, G. (2021a). Dodging DeepFake detection via implicit spatialdomain notch filtering. arXiv preprint arXiv:2009.09213 · arXiv
- Koopman, M., Rodriguez, A. M., & Geradts, Z. (2018). Detection of deepfake video manipulation. In Conference: IMVIP .
- Nhu, T., Na, I., & Kim, S. (2018). Forensics face detection from gans using convolutional neural network. In Proceeding of 2018 international symposium on information technology convergence (ISITC 2018) .
- VanOord,A.,Kalchbrenner,N.,&Kavukcuoglu,K.(2016).Pixelrecurrent neural networks. In: International Conference on Machine Learning, PMLR, pp 1747-1756
- Zhai, L., Juefei-Xu, F., Guo, Q., Xie, X., Ma, L., Feng, W., Qin, S., & Liu, Y. (2022). Adversarial rain attack and defensive deraining for dnn perception. arXiv preprint arXiv:2009.09205 · arXiv
Cited by
Deepfake video detection: challenges and opportunities
Kaur, A., Noori Hoshyar, A., Saikrishna, V., Firmin, S., & Xia, F. (2024) · Artificial Intelligence Review · doi:10.1007/s10462-024-10810-6 · Cited by 214
UVCGAN: UNet Vision Transformer cycle-consistent GAN for unpaired image-to-image translation
Torbunov, D., Huang, Y., Yu, H., Huang, J., Yoo, S., Lin, M., Viren, B., & Ren, Y. (2023) · 2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv56688.2023.00077 · Cited by 189
“Thankfully, there are countermeasures and detection tools [39] developed to counter such misuse.”
BackgroundSelf-citationMasked Relation Learning for DeepFake Detection
Yang, Z., Liang, J., Xu, Y., Zhang, X.-Y., & He, R. (2023) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2023.3249566 · Cited by 143
“terfeit faces of images or videos [3], [4], [5], [6].”
BackgroundDeepfakes: current and future trends
Gambín, Á. F., Yazidi, A., Vasilakos, A., Haugerud, H., & Djenouri, Y. (2024) · Artificial Intelligence Review · doi:10.1007/s10462-023-10679-x · Cited by 145
Das, S., Seferbekov, S., Datta, A., Islam, M. S., & Amin, M. R. (2021) · 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) · doi:10.1109/iccvw54120.2021.00421 · Cited by 107
“A survey of multiple DeepFake detection architectures and their performance comparison has been presented in [20].”
Metadata
- Authors
- Juefei-Xu, F., Wang, R., Huang, Y., Guo, Q., Ma, L., & Liu, Y.
- Affiliations
- Alibaba Group (United States) (US)
- Wuhan University (CN)
- East China Normal University (CN)
- Tianjin University (CN)
- University of Alberta (CA)
- Zhejiang Sci-Tech University (CN)
- Corresponding author
- Wang, Run
- Guo, Qing
- Venue
- International Journal of Computer Vision
- Published
- 2022-05-04
- Volume
- 130
- Issue
- 7
- Pages
- 1678-1734
- ISSN
- 0920-5691 (ISSN-L)
- 1573-1405
- PMC
- PMC9066404
- OpenAlex
- W3135485589
- Cited by
- 191
- References
- 325
- Citations by year
- 2026: 23 · 2025: 53 · 2024: 53 · 2023: 43 · 2022: 11
- FWCI
- 13.09
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Licence
- www.springernature.com/gp/researchers/text-and-data-mining (tdm)
- www.springernature.com/gp/researchers/text-and-data-mining (vor)
- Locations
- International Journal of Computer Vision (publishedVersion)
- PubMed Central (publishedVersion)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- DR-NTU (Nanyang Technological University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Research Foundation Singapore (NRF2018NCR-NCR005-0001, NRF2018NCR-NSOE003-0001)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Face recognition and analysis
- Keywords
- deepfakes, deepfake detection, deepfake generation, adversarial interaction, misinformation, face manipulation, generative adversarial networks
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-09-28, under version 3 of the claim definition (prompt extract-v3).
A second model labelled each claim on 2026-09-28 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.