Making DeepFakes More Spurious: Evading Deep Face Forgery Detection via Trace Removal Attack
Open accessThe DOI matches its Crossref record; 35 of the 35 references it cites were found in a registry or an index.
Abstract
DeepFakes are raising significant social concerns. Although various Despite various DeepFake detectors having been developed as countermeasures, their vulnerability under attacks remains further explorations. Recently, several attacks, such as adversarial attacks, have successfully fooled DeepFake detectors. However, existing attacks suffer from detector-specific designs, requiring detector-side knowledge, leading to poor transferability. Moreover, they only consider simplified security scenarios; but less is known about the attacking performance in complex scenarios where the capability of detectors or attackers varies. To fill the gap, we propose a novel, detector-agnostic trace removal attack. The attack removes all possible counterfeiting traces arising from the original DeepFake manufacture procedure to make DeepFakes essentially more "realistic" and thus able to defeat arbitrary or unknown detectors. Concretely, we first perform an in-depth DeepFake trace discovery, identifying three intrinsic traces: spatial anomalies, spectral disparities, and noise fingerprints. Then an adversarial learning-based trace removal network (TR-Net) involving one generator and multiple discriminators is proposed. Each discriminator is responsible for one individual trace representation to avoid inner-trace interference. All discriminators are optimized in parallel to enforce the generator to remove various traces simultaneously. We additionally craft heterogeneous security scenarios where the detectors are embedded with different levels of defense and the attackers own varying background data knowledge. The experimental results show that the proposed trace removal attack can significantly compromise the detection accuracy of six state-of-the-art DeepFake detectors while causing only a negligible degradation in visual quality.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
U-Net: Convolutional Networks for Biomedical Image Segmentation
Ronneberger, O., Fischer, P., & Brox, T. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24574-4_28 · Cited by 99,404
Towards Evaluating the Robustness of Neural Networks
Carlini, N., & Wagner, D. (2017) · 2017 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2017.49 · Cited by 8,859 · cited 1×
“…classic adversarial attack methods, including Fast Gradient Sign Method (FGSM) [45], iterative FGSM [46], Carlini and Wagner l 2 -norm Attack [47], DeepFool [48] and Projected Gradient Descent (PGD) [49], are explored to expose the vulnerability of DeepFake detectors in both white-and…”
MethodTowards Deep Learning Models Resistant to Adversarial Attacks
Madry, A., Makelov, A., Schmidt, L., Tsipras, D., & Vladu, A. (2017) · arXiv · doi:10.48550/arxiv.1706.06083 · Cited by 6,602
Adversarial examples in the physical world
Kurakin, A., Goodfellow, I. J., & Bengio, S. (2018) · Artificial Intelligence Safety and Security · doi:10.1201/9781351251389-8 · Cited by 5,375
DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks
Moosavi-Dezfooli, S.-M., Fawzi, A., & Frossard, P. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.282 · Cited by 5,317 · cited 1×
“…attack methods, including Fast Gradient Sign Method (FGSM) [45], iterative FGSM [46], Carlini and Wagner l 2 -norm Attack [47], DeepFool [48] and Projected Gradient Descent (PGD) [49], are explored to expose the vulnerability of DeepFake detectors in both white-and black-box scenarios…”
MethodAn overview of gradient descent optimization algorithms
Ruder, S. (2016) · arXiv · doi:10.48550/arxiv.1609.04747 · Cited by 4,962
StarGAN: Unified Generative Adversarial Networks for Multi-domain Image-to-Image Translation
Choi, Y., Choi, M., Kim, M., Ha, J.-W., Kim, S., & Choo, J. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00916 · Cited by 4,163
FaceForensics++: Learning to Detect Manipulated Facial Images
Rossler, A., Cozzolino, D., Verdoliva, L., Riess, C., Thies, J., & Niessner, M. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00009 · Cited by 3,314 · cited 12×
“Regardingtheattacks,theadversarialattackmethods, FGSM and PGD , are particularly destructive to Xception , which is not surprising because they are optimized based on Xception in a white-box manner.”
BackgroundInfluentialRich Models for Steganalysis of Digital Images
Fridrich, J., & Kodovsky, J. (2012) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2012.2190402 · Cited by 2,144 · cited 1×
“AnSRMfilterisadopted forthispurposegivenitseffectivenessinestimatinglocalnoise distributions for image forensics [54].”
Deepfakes and beyond: A Survey of face manipulation and fake detection
Tolosana, R., Vera-Rodriguez, R., Fierrez, J., Morales, A., & Ortega-Garcia, J. (2020) · Information Fusion · doi:10.1016/j.inffus.2020.06.014 · Cited by 1,237
Face X-Ray for More General Face Forgery Detection
Li, L., Bao, J., Zhang, T., Yang, H., Chen, D., Wen, F., & Guo, B. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00505 · Cited by 1,211
CNN-Generated Images Are Surprisingly Easy to Spot… for Now
Wang, S.-Y., Wang, O., Zhang, R., Owens, A., & Efros, A. A. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00872 · Cited by 1,210
The Emergence of Deepfake Technology: A Review
Westerlund, M. (2019) · Technology Innovation Management Review · doi:10.22215/timreview/1282 · Cited by 1,138
Thinking in Frequency: Face Forgery Detection by Mining Frequency-Aware Clues
Qian, Y., Yin, G., Sheng, L., Chen, Z., & Shao, J. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58610-2_6 · Cited by 1,058
Exploiting Visual Artifacts to Expose Deepfakes and Face Manipulations
Matern, F., Riess, C., & Stamminger, M. (2019) · 2019 IEEE Winter Applications of Computer Vision Workshops (WACVW) · doi:10.1109/wacvw.2019.00020 · Cited by 824
Exposing DeepFake Videos By Detecting Face Warping Artifacts
Li, Y., & Lyu, S. (2018) · arXiv · doi:10.48550/arxiv.1811.00656 · Cited by 785 · cited 2×
“Spatial anomalies can also be found in faces generated by model templates, due to the manufacturing failures during the template alignment or rendering [27], [50].”
BackgroundGeneralizing Face Forgery Detection with High-frequency Features
Luo, Y., Zhang, Y., Yan, J., & Liu, W. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01605 · Cited by 609
Spatial-Phase Shallow Learning: Rethinking Face Forgery Detection in Frequency Domain
Liu, H., Li, X., Zhou, W., Chen, Y., He, Y., Xue, H., Zhang, W., & Yu, N. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00083 · Cited by 600
Self-citationDetecting and Simulating Artifacts in GAN Fake Images
Zhang, X., Karaman, S., & Chang, S.-F. (2019) · 2019 IEEE International Workshop on Information Forensics and Security (WIFS) · doi:10.1109/wifs47025.2019.9035107 · Cited by 567 · cited 2×
“Zhang et al. [37] identify unknown DeepFakes by detecting and simulating general spectrum artifacts.”
BackgroundDeepFakes: a New Threat to Face Recognition? Assessment and Detection
Korshunov, P., & Marcel, S. (2018) · arXiv · doi:10.48550/arxiv.1812.08685 · Cited by 497 · cited 8×
“The disparity patterns in the DeepfakeTIMIT images differs from the other two because only DeepfakeTIMIT involves a post-processing procedure that further change the spectral distribution.”
BackgroundInfluentialGlobal Texture Enhancement for Fake Face Detection in the Wild
Liu, Z., Qi, X., & Torr, P. H. S. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00808 · Cited by 401
Leveraging Frequency Analysis for Deep Fake Image Recognition
Frank, J., Eisenhofer, T., Schönherr, L., Fischer, A., Kolossa, D., & Holz, T. (2020) · arXiv · doi:10.48550/arxiv.2003.08685 · Cited by 390 · cited 4×
“For instance, Durall et al. [33], Dzanic et al. [34] and Frank et al. [35] determined that there were Fourier spectrum discrepancies between CNN-generated images and real images which could be efficiently captured by a shallow machine learning classifier.”
BackgroundMethodInfluentialDo GANs leave artificial fingerprints?
Marra, F., Gragnaniello, D., Verdoliva, L., & Poggi, G. (2019) · 2019 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR) · doi:10.1109/mipr.2019.00103 · Cited by 361
What Makes Fake Images Detectable? Understanding Properties that Generalize
Chai, L., Bau, D., Lim, S.-N., & Isola, P. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58574-7_7 · Cited by 357
Local Relation Learning for Face Forgery Detection
Chen, S., Yao, T., Chen, Y., Ding, S., Li, J., & Ji, R. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i2.16193 · Cited by 334
DeepFake Detection Based on Discrepancies Between Faces and Their Context
Nirkin, Y., Wolf, L., Keller, Y., & Hassner, T. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3093446 · Cited by 312 · cited 3×
“Although the latest GANs significantly improve on visual quality over their predecessors, some subtle unnatural traces such as textural inconsistencies and contextual discrepancies can still occur [22], [23], [24], [25], [26].”
BackgroundAdversarial Deepfakes: Evaluating Vulnerability of Deepfake Detectors to Adversarial Examples
Hussain, S., Neekhara, P., Jere, M., Koushanfar, F., & McAuley, J. (2021) · 2021 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv48630.2021.00339 · Cited by 204
Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Data
Yu, N., Skripniuk, V., Abdelnabi, S., & Fritz, M. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01418 · Cited by 195
Evading Deepfake-Image Detectors with White- and Black-Box Attacks
Carlini, N., & Farid, H. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw50498.2020.00337 · Cited by 170
A Robust GAN-Generated Face Detection Method Based on Dual-Color Spaces and an Improved Xception
Chen, B., Liu, X., Zheng, Y., Zhao, G., & Shi, Y.-Q. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2021.3116679 · Cited by 125 · cited 2×
“Although the latest GANs significantly improve on visual quality over their predecessors, some subtle unnatural traces such as textural inconsistencies and contextual discrepancies can still occur [22], [23], [24], [25], [26].”
BackgroundAdversarial 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
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 · cited 1×
“Therearealsoseveralstudies[16],[29],[30] thatinvestigatethepowerofdeepconvolutionalneuralnetworks (CNNs),suchasXception[31]andResNet[32],inDeepFake detectionfromadata-drivenperspective.”
A 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 · cited 2×
“Previous studies attributed this phenomenon to the transposed convolution operation, a widely-used upsampling unit in CNN-based generative models for increasing feature dimensionality [33], [35], [36], [37], [52].”
BackgroundMethodGANprintR: 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 by
DeepFake Detection Based on High-Frequency Enhancement Network for Highly Compressed Content
Gao, J., Xia, Z., Marcialis, G. L., Dang, C., Dai, J., & Feng, X. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.123732 · Cited by 67
On the Vulnerability of Deepfake Detectors to Attacks Generated by Denoising Diffusion Models
Ivanovska, M., & Štruc, V. (2024) · 2024 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW) · doi:10.1109/wacvw60836.2024.00115 · Cited by 16
Liu, P., Tao, Q., & Zhou, J. (2024) · Proceedings of the 1st ACM Multimedia Workshop on Multi-modal Misinformation Governance in the Era of Foundation Models · doi:10.1145/3689090.3689386 · Cited by 3
Metadata
- Authors
- Liu, C., Chen, H., Zhu, T., Zhang, J., & Zhou, W.
- Venue
- IEEE Transactions on Dependable and Secure Computing
- Published
- 2023-11
- Volume
- 20
- Issue
- 6
- Pages
- 5182-5196
- ISSN
- 1545-5971 (ISSN-L)
- 1941-0018
- 2160-9209
- OpenAlex
- W4318954125
- Cited by
- 60
- References
- 35
- FWCI
- 5.36
- Type
- journal article
- Language
- en
- Open access
- green
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.
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.