The DOI matches its Crossref record; 21 of the 21 references it cites were found in a registry or an index.
Detecting and Simulating Artifacts in GAN Fake Images
Open accessAbstract
To detect GAN generated images, conventional supervised machine learning algorithms require collecting a large number of real images as well as fake images generated by the targeted GAN model. However, the specific model used by the attacker is often unavailable. To address this, we propose a GAN simulator, AutoGAN, which can simulate the artifacts produced by the common pipeline shared by several popular GAN models. Additionally, we identify a unique artifact caused by the up-sampling component included in the common GAN pipelines. We show theoretically such artifacts are manifested as replications of spectra in the frequency domain and thus propose a classifier model based on the spectrum input, rather than the pixel input. By using the simulated images to train a spectrum based classifier, even without seeing the fake images produced by the targeted GAN model during training, our approach achieves state-of-the-art performances on detecting fake images generated by popular GAN models such as CycleGAN.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“Figure 7 represents the potentials of employing the frequency artifacts for detecting DeepFakes, where the GAN-based manipulation introduces invisible artifacts in the frequency domain.”
From Countering Malicious DeepFakes: Survey, Battleground, and Horizon (2022) · cites this paper as Zhang et al. 2019
In the citing paper
“Due to limited data, network structure,8 and optimization algorithms,6 the GANs can hardly fit the distribution of real data.”
From Deepfakes: A new threat to image fabrication in scientific publications? (2022) · cites this paper as [8]
In the citing paper
“The most well-known artifact is the checkerboard effect due to the image upsampling operation in GAN.8”
From Deepfakes: A new threat to image fabrication in scientific publications? (2022) · cites this paper as [8]
Citations
Cites
Unpaired image-to-image translation using cycle-consistent adversarial networks
Zhu, J.-Y., Park, T., Isola, P., & Efros, A. A. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.244 · Cited by 23,602
Image-to-Image Translation with Conditional Adversarial Networks
Isola, P., Zhu, J.-Y., Zhou, T., & Efros, A. A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.632 · Cited by 22,930 · cited 1×
“image that is constrained by the layout of the sketch [11], [6], [10].”
BackgroundLabaca-Castro, R. (2023) · Springer eBooks · doi:10.1007/978-3-658-40442-0_9 · Cited by 21,119
GAN（Generative Adversarial Nets）
淳司, 柴. (2017) · Journal of Japan Society for Fuzzy Theory and Intelligent Informatics · doi:10.3156/jsoft.29.5_177_2 · Cited by 20,507
Unsupervised representation learning with deep convolutional generative adversarial networks
Radford, A., Metz, L., & Chintala, S. (2015) · arXiv · doi:10.48550/arxiv.1511.06434 · Cited by 12,235 · cited 1×
“a deconvolution) [19], [6], [7] and nearest neighbor interpolation [9], [10].”
BackgroundA Style-Based Generator Architecture for Generative Adversarial Networks
Karras, T., Laine, S., & Aila, T. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00453 · Cited by 11,714 · cited 2×
“In image generation, GAN [1] can be applied in the following scenarios: 1) taking noise as input to produce an image [9], [2], [3]; 2) taking an image from one semantic category (such as horse) as input to produce an image of another semantic category (such as zebra) [6], [7], [10]; 3) taking a sketch or a pixel level…”
BackgroundMethodProgressive Growing of GANs for Improved Quality, Stability, and Variation
Karras, T., Aila, T., Laine, S., & Lehtinen, J. (2017) · arXiv · doi:10.48550/arxiv.1710.10196 · Cited by 4,727 · cited 4×
“) [6] and nearest neighbor interpolation (NN) [9].”
BackgroundMethodInfluentialStarGAN: 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
Large Scale GAN Training for High Fidelity Natural Image Synthesis
Brock, A., Donahue, J., & Simonyan, K. (2018) · arXiv · doi:10.48550/arxiv.1809.11096 · Cited by 3,717 · cited 2×
“In image generation, GAN [1] can be applied in the following scenarios: 1) taking noise as input to produce an image [9], [2], [3]; 2) taking an image from one semantic category (such as horse) as input to produce an image of another semantic category (such as zebra) [6], [7], [10]; 3) taking a sketch or a pixel level…”
BackgroundMethodSemantic Image Synthesis With Spatially-Adaptive Normalization
Park, T., Liu, M.-Y., Wang, T.-C., & Zhu, J.-Y. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00244 · Cited by 2,974 · cited 5×
“However, all classifiers fail on GauGAN images, since the generator structure of GauGAN (5 nearest neighbor up-samplers) is drastically different from the CycleGAN structure.”
BackgroundMethodInfluential
Cited by
Sorted by citations
Items 501–561 of 561
Detection of AI-Generated Fake Images Using Xception Model
Khatri, A., & Gupta, N. (2025) · International Conference on Information Systems and Computer Networks (ISCON) · doi:10.1109/iscon65210.2025.11341496
“Artificial Neural Networks have demonstrated great promise in tackling this problem, particularly when combined with Convolutional Neural Networks (CNNs) [1–4], [4–7].”
Lightweight Deepfake Detection Application Using SFTNet
Ip, C. S., Wong, H. L., Sum, K. W., & Tsang, C. S. C. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11342702
“…networks (GANs), which introduce substantial spectral artifacts through interpolation errors and aliasing effects, as noted in studies by Frank et al. [7] and others [27] Recent work has further highlighted the utility of frequency-domain analysis as a diagnostic tool for deepfake detection.”
Identification of Generative Forged Western Blot Images
Zhang, Y., Tan, S., & Huang, J. (2025) · IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom) · doi:10.1109/trustcom66490.2025.00145
“Zhang et al. [15] simulated GAN upsam-pling to produce controllable frequency artifacts, and Frank et al. [16] analyzed high-frequency noise consistently present in various generative models.”
Adaptive Multi-Feature Hierarchical Framework for Generative Model Attribution
Wang, R., Li, L., Si, X., Yuan, K., & Wang, Z. (2025) · IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom) · doi:10.1109/trustcom66490.2025.00391
“Zhang et al. [7] proposed a hybrid feature space for distinguishing GAN variants, while Yu et al. [8] exploited weak noise residuals as fingerprints for source attribution.”
InfluentialNeural Threats: Cybersecurity Implications of CNN- and RNN-Based Deepfake Detection
Kotari, M., Kurundwade, P., R, P. K., Talawar, P. I., & Roshan, S. (2025) · IEEE Global Conference for Advancement in Technology (GCAT) · doi:10.1109/gcat66372.2025.11368557 · Cited by 1
“[7] As most deepfake algorithms have difficulty detecting high-resolution details, affine transformation artifacts gave valid manipulation hints.”
Forged anomaly detection using advanced deep learning
Choudhry, N., Abawajy, J., Huda, S., & Rao, I. (2026) · Applied Intelligence · doi:10.1007/s10489-026-07114-3
“In the field of generic image forgery detection, the pri - mary objective is to distinguish authentic images from those generated by CNNs. Zhang et al. [32] highlight the diffi - culty classifiers face in generalizing across various GANs, often relying on upsampling artifacts.”
Perceptual Classifiers: Detecting Generative Images Using Perceptual Features
Durbha, K. S., Venkataramanan, A. K., Sureddi, R., & Bovik, A. C. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00357
“[60] and Frank et al .”
AdvOSD: Adversarial One-Step Diffusion for Generalizable and Efficient Fake Image Detection
Shan, L., Han, K., Tu, Y., & Hei, X. (2025) · Annual Computer Security Applications Conference · doi:10.1109/acsac67867.2025.00082
“We evaluate our AdvOSD against several strong baselines, including CNN-Spot [24], Patchor [52], Co-occurrence [53], Freq-spec [54], F3Net [55], UniFD [12], LGrad [38], FreqNet [56], NPR [57], FatFormer [14], C2P-CLIP [16].”
Semantic Distribution and Authenticity Discrepancy Alignment for AI-Generated Image Detection
Zhang, J., Li, L., Yan, C. C., Ke, W., & Gong, Y. (2026) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2026.3668513 · Cited by 1
Song, Y., Kuang, J., & Xu, R. (2026) · IEEE Access · doi:10.1109/access.2026.3669419 · Cited by 1
“For example, methods detecting unnatural edge transitions [2] and analyzing image spectral characteristics [3] achieved notable success in identifying inconsistencies introduced by early forgery techniques.”
Deep hashing framework for proactively deepfake retrieval and detection
Liu, X., Cheng, A., Xiao, M., Li, X., & Zhao, Y. (2026) · Journal of King Saud University - Computer and Information Sciences · doi:10.1007/s44443-026-00636-3
“For more detailed extraction of detection clues, Zhang et al. (2019) propose a simulator to simulate the checker-board artifacts in the frequency domain which caused by the up-sampling operations of generated images.”
A Study on Deep Fake Detection and Content Suspension Mechanisms from Creation to Control
Rallapalli, S., Sowmya, J., & Dileep, M. R. (2025) · International Conference on Recent Trends in Electrical, Electronics and Computing Technologies (ICRTEECT) · doi:10.1109/icrteect67512.2025.11448651
“Zhang et al.[8] presented a method for identifying and simulating artifacts in GAN-generated images.”
A Frequency-Aware Suppression Masking for Generalized Deepfake Detection
Ilame, S., & Kumar, A. (2025) · International Conference on Data Science and Intelligent Network Computing (ICDSINC) · doi:10.1109/icdsinc66221.2025.11448231
“Zhang et al. [25] introduced AutoGAN, a method that simulates upsampling artifacts from common GAN pipelines and uses frequency-based features to detect fakes, even from unseen models.”
Background-Noise-Driven Detection of Diffusion-Generated Images
Li, J., Ou, W., Meng, D., & Xu, Y. (2026) · IEEE Signal Processing Letters · doi:10.1109/lsp.2026.3678476
Detection of computer-generated images via deep learning
Quan, W. (2020) · theses.fr (ABES) · doi:10.70675/94785333zc081z4ed5z8863zfafa784de991
Gonthier, N. (2021) · theses.fr (ABES) · doi:10.70675/9abc66b4zca61z423bz85dcz07b849b15209
Detection of Diffusion-Generated Images Using CBAMEnhanced Pre-Trained CNNs
Çetintaş, D., & Yücel, Z. (2026) · Acta Infologica · doi:10.26650/acin.1726320
Physically constrained generative networks for cloud and texture synthesis
Chatillon, P. (2023) · theses.fr (ABES) · doi:10.70675/847251bcz5a74z492fz9ac0z77d1e9962653
Structure searchable network model for deepfake image detection
Liu, Z., Wang, X., Wang, Q., Bai, N., Han, R., & Pang, S. (2026) · Pattern Recognition · doi:10.1016/j.patcog.2026.113813
VTONGuard: Automatic Detection and Authentication of AI-generated Virtual Try-On Content
Wu, S., Hong, Y., Chen, S., Wang, Z., Sun, X., Zhan, J., Lan, J., & Zhang, J. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11463297
Structure-Adaptive Basis Shrinkage for Generalizable Deepfake Detection
Sun, B., Gong, M., Li, Z., Wu, Y., & Liu, H. (2025) · China Automation Congress (CAC) · doi:10.1109/cac67268.2025.11486961
AI-Generated Image Detection: Challenges and Recent Advances
Koutlis, C., Corvi, R., Cozzolino, D., Bammey, Q., Konstantinidou, D., Schinas, M., Karageorgiou, D., Verdoliva, L., & Papadopoulos, S. (2026) · Springer eBooks · doi:10.1007/978-3-032-11782-3_6
MFD: Deep Fake Image Detection Based on Multi-Scale Frequency Domain Feature Fusion
Liu, Y., Cui, S., Deng, R., & Chen, Y. (2026) · Asia Conference on Algorithms, Computing and Machine Learning (CACML) · doi:10.1109/cacml68972.2026.11507120
“Improve the FEM module in FFCA-YOLO [11] by adopting a parallel branch structure to enhance multi-scale feature extraction.”
Quality-Guided Forgery Adapter for Generalizable AIGC Image Detection
Wang, J., Yu, Z., Chen, C., Gu, L., Wan, W., Zhou, J., & Zhang, W. (2026) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2026.3698571 · Cited by 1
“Some algorithms also rely on specific forensic traces, such as distinguishable characteristics in the color space [14], [15] and spectral regularities in synthetic images [9], [16], [17], [18].”
A Lightweight Framework for Emotion Drift and Asymmetry Detection in Explainable Deepfake Analysis
Vishwajeeth, S., Balachandra, Dayakshini, & Rao, S. (2026) · International Conference on Artificial Intelligence and Data Engineering (AIDE) · doi:10.1109/aide69088.2026.11544732
“Frequency artifacts were targeted by Zhang et al. [7], while Agarwal et al. studied phoneme–viseme mismatches for audio–visual coherence [8].”
Adasa: Cross-Domain Deepfake Detection Using Multi-Stream Multimodal Fusion
Almaazmi, H., Alblooshi, A., & Alkhatib, M. (2026) · Student Research Conference on Applied Computing (SRC) · doi:10.1109/src70627.2026.11550678
“As synthetic images become increasingly photorealistic and widely accessible, robust deepfake detection has become a critical problem for digital forensics and cybersecurity [1]– [3].”
Chittam, S., Dasgupta, S., Luitel, S., Siddula, M., & Roy, K. (2026) · Research Square · doi:10.21203/rs.3.rs-9707209/v1
Zheng, Y., Ahn, H., Lee, J., & Park, E. (2026) · International Conference on Multimedia Retrieval · doi:10.1145/3805622.3810639
“We include AutoGAN [51], DIRE [49], De-Fake [43], ZeroFake [44], LaRE [32], CLIPping (Linear Probing/Prompt Tuning) [22], LOTA [48], and SAFE [29] as baselines.”
Vahdati, D. S., Nguyen, T. D., Azizpour, A., Ahangari, H., & Stamm, M. C. (2026) · ACM Workshop on Information Hiding and Multimedia Security (IH&MMSec) · doi:10.1145/3785353.3815083
“…improve rapidly, research has pivoted to using forensic microstructures - invisible, semantic-independent, neighboring pixel-level relationships - that arise from the distinct processing pipelines in a camera imaging system or a GenAI model’s architecture and generation processes [15, 61, 69].”
Qiu, M.-X., Chuang, K., & Lai, S. (2026) · International Conference on Automatic Face and Gesture Recognition · doi:10.1109/fg67764.2026.11556934
“Standard detection pipelines naively average the predictions of clips or frames [14], [15], [24], [37], [58], [45], [29], [53], [54], [55], [57] to get an overall video-level prediction, severely diluting signals from artifact-rich segments in partially forged videos.”
Exposing GANfakes: a systematic review of cutting-edge detection and localization techniques
Salmani, S. B., & Nimkar, A. V. (2026) · Multimedia Tools and Applications · doi:10.1007/s11042-026-21735-3
“Pre-trained architectures—XceptionNet, ResNet, DenseNet, and InceptionNet—have demonstrated strong baseline performance across multiple GAN detection benchmarks [83, 126, 137].”
InfluentialDeep learning for CGI and visual forgery detection: a comprehensive survey
Korkmaz, A., & Özden, M. (2026) · International Journal of Data Science and Analytics · doi:10.1007/s41060-026-01192-9
Iqbal, S., & Munir, M. W. (2026) · International Conference on IT and Industrial Technologies (ICIT) · doi:10.1109/icit68548.2026.11577683
Wang, J., Luo, Q., & Jeon, G. (2026) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd68734.2026.11582378
“Frequency-domain approaches like Spec [12] capture periodic artifacts through spectral energy distribution, while PatchCraft [13] enhances discrimination via texture contrast.”
F-BAD: A frequency-driven black-box active defense framework against facial forgery
Chang, Q., Wang, Z., Liu, X., Chen, Y., Yao, Y., Li, X., & Zhao, Y. (2026) · Displays · doi:10.1016/j.displa.2026.103631
Demirci, M., & Öznur, S. A. R. I. (2026) · European Journal of Theoretical and Applied Sciences · doi:10.59324/ejtas.2026.4(4).04
FAIR: Feature-Augmented Implicit Regularization for AI-Generated Fake Image Detection
Haque, M. R., Murshed, M., Paul, M., & Lee, T.-K. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37321-2_32
Learning Generalizable Visual Representations for AI-Generated Image Detection
Ghanim, R., & Hmaizah, N. (2026) · Al-Noor Journal of Engineering Management and Computer Science · doi:10.71229/4kj12980
SEED-Net: Spectral-Embedded Efficient Detection Network for Cross-Domain Face Forgery Detection
Zhang, X., Zhang, B., & Chaudhary, V. (2026) · IEEE/ACIS International Conference on Software Engineering Research, Management and Applications (SERA) · doi:10.1109/sera69989.2026.11618602
“A key observation is that different forgery methods introduce artifacts at different frequency scales [5], [20].”
Self-citationEutamene, H. B., Sellam, A. Z., Ahmed, A. T., & Hadid, A. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-31927-2_7
Abdullah, A., Ebert, N., & Wasenmüller, O. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-31335-5_18
Lightweight Detection of AIGI Based on Multi-Feature Fusion and Phased Optimization
Li, Y., Zhang, X., Wang, H., Cui, H., & Zhu, Y. (2026) · IEEE International Conference on Computer Vision and Deep Learning (DLCV) · doi:10.1109/dlcv69906.2026.11635629
“…methods address upsampling artifacts in generative models; Zhang et al. discovered spectral replication features in GAN-generated images [12], while Frank et al.’s FreDect enhances detection performance through DCT frequency-domain features [13]; Methods based on pre-trained models…”
Self-citationKaracan, M. H., & Yücebaş, S. C. (2026) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-026-02182-w
Suspicious Frequency Amplified Hybrid Framework for Generalizable AIGC Image Detection
Wang, J., Zou, J., Yu, Z., Ye, S., Wan, W., Gu, L., Zhou, J., & Zhang, W. (2026) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2026.3723118
“Another golden rule that applies equally well to improving generalization performance is considering frequency features [15], [34], [35], [12], [36], [37], [33].”
A Swin Transformer and CLIP-Based Framework for Generalized DeepFake Detection
Li, S., & Zhou, S. (2026) · Lecture notes in electrical engineering · doi:10.1007/978-981-95-6825-3_10
Edge-based perceptual feature in GANs for image denoising
Limsuebchuea, A., Duangsoithong, R., & de Herrera, A. G. S. (2026) · Pattern Analysis and Applications · doi:10.1007/s10044-026-01760-6
“( 2). where w old represents the weight before adjustment in the current round, ∂ e total ∂ w corresponds to the error difference between the current and previous rounds, and η denotes the learning rate, defining the learning speed.”
ASAP: Visual analytics for identifying and analyzing image patterns in AI-generated images
Huang, J., Ueno, Y., Chen, C., Mishra, A., Kwon, B. C., Liu, Z., & Bryan, C. (2026) · Information Visualization · doi:10.1177/14738716261481077 · Cited by 7
“While the research community has developed examples of automated detection methods for fake images (that can outperform human experts under certain conditions 8 ), these tools often face significant challenges, including generalizability 9 , interpretability 10–12 , and actionability 10 .”
Nguyen, T.-V., Ngo, K. H. A., & Ngo, K. H. A. (2026) · International Conference on Image, Vision and Computing (ICIVC) · doi:10.1109/icivc70586.2026.11686669
“Zhang et al. [16] proposed AutoGAN to simulate and detect artifacts characteristic of the standard GAN pipeline, demonstrating that a general-purpose detector can be built by exploiting common features of the AI synthesis process rather than relying on generator-specific detectors.”
$$\mu $$Flow: Leveraging Average Images for Improving Generalisation of Deepfake Faces Detectors
Pontorno, O., Litrico, M., Guarnera, L., Giuffrida, M. V., & Battiato, S. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37422-6_20 · Cited by 1
Fan, L., & Roberson, J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-39379-1_42
EIRES:Training-free AI-Generated Image Detection via Edit-Induced Reconstruction Error Shift
Jiang, W., Yan, J., Chen, X., Shen, L., Lin, C., Diao, Y., & Hong, R. (2026) · doi:10.1109/cvprf71909.2026.00623
“ME consistently achieves the best performance across all generators, demonstrating that aggregating multiple edits yields a more stable and discriminative detection signal than any single edit alone.”
ForenDeX: Unlocking Forensic Insights for Explainable AI-Generated Image Detection
Tan, C., Wang, J., Xiang, M., Tao, R., Wei, Y., Zhao, Y., & Lu, Y. (2026) · doi:10.1109/cvprf71909.2026.00633 · Cited by 1
In2CLR: Joint Intra-Inter Curriculum Learning with Review for Degraded Fake Image Detection
Li, Y., Liu, B., Wu, Y., & Li, R. (2026) · doi:10.1109/cvprf71909.2026.00234
“We further compared In2CLR with several mainstream detection methods, including DeiT-S, Swin-T, CNNSpot [28], Spec [30], and F3Net models, as shown in Table 4.”
Yang, Y., Li, Y., Huang, H., Li, Z., Du, B., & Wu, Y. (2026) · doi:10.1109/cvprf71909.2026.00770
“…data, and even the initialization parameters [5, 8, 9, 28, 52, 55]; generic artifacts results from the shared computational components across generators (e.g., upsampling operations) [5, 8, 28, 44, 47, 55]; real image traits stemming from physical photographic and imaging processes [17, 22, 26].”
InfluentialPRADA: Probability-Ratio-Based Attribution and Detection of Autoregressive-Generated Images
Damm, S., Ricker, J., Petzka, H., & Fischer, A. (2026) · doi:10.1109/cvprf71909.2026.00625
“A particularly well-explored approach is the analysis of frequency artifacts in GAN-generated images [20, 21, 25, 86], which has also been studied for DMs [12, 61].”
Chen, L., & Ding, Y. (2026) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2026.3744649
Dynamic Mask Guided Synthetic Image Detection via Mid-Frequency Enhanced Diffusion Priors
Wang, Q., Ba, G., Yin, J., & Zou, C. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11729947
Toward Efficient, Explainable Satellite Deepfake Detection: Colour and Frequency Band Contributions
Ziulu, V., & Garforth, J. (2026) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss60577.2026.11730957
“This finding is consistent with prior work [44], which showed that deepfake generation pipelines struggle to reproduce fine-grained textures.”
Quantum-Empowered Optical-Radar Fusion of Sentinel-1 and Sentinel-2 Data for Reliable Cloud Removal
You, X.-Y., Lin, C.-H., & Hsu, S. (2026) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss60577.2026.11731424
“In certain instances, this may lead to the generation of plausible but non-existent details [21, 22].”
ForensicTransfer: Weakly-supervised Domain Adaptation for Forgery Detection
Cozzolino, D., Thies, J., Rössler, A., Riess, C., Nießner, M., & Verdoliva, L. (2018) · arXiv · doi:10.48550/arxiv.1812.02510 · Cited by 221
“Some papers have focused their effort in the detection of manipulations on faces [3, 20] or GAN generated images [35, 53].”
Background
Metadata
- Authors
- Zhang, X., Karaman, S., & Chang, S.-F.
- Affiliations
- Columbia University (US)
- Venue
- 2019 IEEE International Workshop on Information Forensics and Security (WIFS)
- Publisher
- IEEE
- Published
- 2019-12
- Pages
- 1-6
- ISSN
- 2157-4774 (ISSN-L)
- OpenAlex
- W3012472557
- Cited by
- 567
- References
- 21
- Citations by year
- 2026: 60 · 2025: 113 · 2024: 89 · 2023: 100 · 2022: 84 · 2021: 81 · 2020: 39
- FWCI
- 16.52
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE International Workshop on Information Forensics and Security (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- 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 › Artificial Intelligence › Adversarial Robustness in Machine Learning
- Keywords
- GAN-generated image detection, CycleGAN, adversarial image generation
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
