mlsanityData to 7 Oct 2026

Countering Malicious DeepFakes: Survey, Battleground, and Horizon

arXiv 2103.00218 ↗First posted 27 Feb 2021cs.CVcited by 56

Not on the map. Why?

Abstract (arXiv)

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 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.

Key facts. Cited by 56 papers in the map (data through 7 Oct 2026). Builds on 192 of its 333 references that are in the map. First posted on arXiv 27 Feb 2021.

Builds on

192 of 333 references.

References · 192

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  5. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  6. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  7. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  8. 2013Auto-Encoding Variational Bayescited by 3,980
  9. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,848
  10. 2018Neural Ordinary Differential Equationscited by 3,733
  11. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  12. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
38 more
  1. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  2. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  3. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  4. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  5. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,320
  6. 2017Improved Training of Wasserstein GANscited by 2,223
  7. 2015Variational Inference with Normalizing Flowscited by 2,161
  8. 2014Conditional Generative Adversarial Netscited by 2,152
  9. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  10. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
  11. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
  12. 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,376
  13. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  14. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,295
  15. 2018Demystifying MMD GANscited by 1,268
  16. 2017Deep Image Priorcited by 1,097
  17. 2019FaceForensics++: Learning to Detect Manipulated Facial Imagescited by 1,095
  18. 2019StarGAN v2: Diverse Image Synthesis for Multiple Domainscited by 1,095
  19. 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,036
  20. 2021Transformers in Vision: A Surveycited by 1,009
  21. 2019An Introduction to Variational Autoencoderscited by 997
  22. 2017VGGFace2: A dataset for recognising faces across pose and agecited by 911
  23. 2016Conditional Image Generation with PixelCNN Decoderscited by 859
  24. 2019CNN-generated images are surprisingly easy to spot... for nowcited by 842
  25. 2016Pixel Recurrent Neural Networkscited by 814
  26. 2020Face2Face: Real-time Face Capture and Reenactment of RGB Videoscited by 631
  27. 2016MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognitioncited by 621
  28. 2018Free-Form Image Inpainting with Gated Convolutioncited by 594
  29. 2018Generative Image Inpainting with Contextual Attentioncited by 578
  30. 2019Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensicscited by 573
  31. 2020Thinking in Frequency: Face Forgery Detection by Mining Frequency-aware Cluescited by 518
  32. 2017Adversarial Patchcited by 514
  33. 2020Leveraging Frequency Analysis for Deep Fake Image Recognitioncited by 501
  34. 2019Face X-ray for More General Face Forgery Detectioncited by 469
  35. 2018Learning to See in the Darkcited by 459
  36. 2014Learning Face Representation from Scratchcited by 451
  37. 2020One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencingcited by 438
  38. 2018MesoNet: a Compact Facial Video Forgery Detection Networkcited by 409

50 most cited of 192 All 192 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 7; 2023: 14; 2024: 17; 2025: 8; 2026: 7.

56 papers.

Sort:

By area:

  1. 2023Anti-DreamBooth: Protecting users from personalized text-to-image synthesiscited by 114
  2. 2024FIRE: Robust Detection of Diffusion-Generated Images via Frequency-Guided Reconstruction Errorcited by 46
  3. 2023SepMark: Deep Separable Watermarking for Unified Source Tracing and Deepfake Detectioncited by 43
  4. 2022UVCGAN: UNet Vision Transformer cycle-consistent GAN for unpaired image-to-image translationcited by 42
  5. 2023Improving Fairness in Deepfake Detectioncited by 40
  6. 2023Evading DeepFake Detectors via Adversarial Statistical Consistencycited by 37
  7. 2023Contrast-Phys+: Unsupervised and Weakly-supervised Video-based Remote Physiological Measurement via Spatiotemporal Contrastcited by 33
  8. 2024Lips Are Lying: Spotting the Temporal Inconsistency between Audio and Visual in Lip-Syncing DeepFakescited by 32
  9. 2021AVA: Adversarial Vignetting Attack against Visual Recognitioncited by 29
  10. 2022GAN-generated Faces Detection: A Survey and New Perspectivescited by 29
  11. 2022Digital and Physical Face Attacks: Reviewing and One Step Furthercited by 17
  12. 2024PolyGlotFake: A Novel Multilingual and Multimodal DeepFake Datasetcited by 16
38 more
  1. 2023Unified Frequency-Assisted Transformer Framework for Detecting and Grounding Multi-Modal Manipulationcited by 14
  2. 2024SoK: Systematization and Benchmarking of Deepfake Detectors in a Unified Frameworkcited by 14
  3. 2022A Review of Deep Learning-based Approaches for Deepfake Content Detectioncited by 12
  4. 2023GenConViT: Deepfake Video Detection Using Generative Convolutional Vision Transformercited by 12
  5. 2024Are Watermarks Bugs for Deepfake Detectors? Rethinking Proactive Forensicscited by 12
  6. 2024A Survey of Defenses Against AI-Generated Visual Media: Detection,Disruption, and Authenticationcited by 12
  7. 2023What can Discriminator do? Towards Box-free Ownership Verification of Generative Adversarial Networkcited by 10
  8. 2024A Timely Survey on Vision Transformer for Deepfake Detectioncited by 10
  9. 2025LOTA: Bit-Planes Guided AI-Generated Image Detectioncited by 10
  10. 2023Towards Prompt-robust Face Privacy Protection via Adversarial Decoupling Augmentation Frameworkcited by 9
  11. 2025NullSwap: Proactive Identity Cloaking Against Deepfake Face Swappingcited by 8
  12. 2021ArchRepair: Block-Level Architecture-Oriented Repairing for Deep Neural Networkscited by 7
  13. 2023Evading Forensic Classifiers with Attribute-Conditioned Adversarial Facescited by 6
  14. 2024Evolving from Single-modal to Multi-modal Facial Deepfake Detection: Progress and Challengescited by 6
  15. 2024PID: Prompt-Independent Data Protection Against Latent Diffusion Modelscited by 6
  16. 2023Real-time Detection of AI-Generated Speech for DeepFake Voice Conversioncited by 5
  17. 2025Unleashing the Potential of Consistency Learning for Detecting and Grounding Multi-Modal Media Manipulationcited by 5
  18. 2022Expressive Talking Head Video Encoding in StyleGAN2 Latent-Spacecited by 4
  19. 2024Semantics-Oriented Multitask Learning for DeepFake Detection: A Joint Embedding Approachcited by 4
  20. 2026Layer Consistency Matters: Elegant Latent Transition Discrepancy for Generalizable Synthetic Image Detectioncited by 4
  21. 2022A comprehensive survey on semantic facial attribute editing using generative adversarial networkscited by 3
  22. 2023Visual Realism Assessment for Face-swap Videoscited by 3
  23. 2023Feature Extraction Matters More: Universal Deepfake Disruption through Attacking Ensemble Feature Extractorscited by 3
  24. 2026Diffusion Epistemic Uncertainty with Asymmetric Learning for Diffusion-Generated Image Detectioncited by 3
  25. 2023Representing Noisy Image Without Denoisingcited by 2
  26. 2024Tex-ViT: A Generalizable, Robust, Texture-based dual-branch cross-attention deepfake detectorcited by 2
  27. 2024Time Step Generating: A Universal Synthesized Deepfake Image Detectorcited by 2
  28. 2025Do DeepFake Attribution Models Generalize?cited by 2
  29. 2025Semantic-Aware Reconstruction Error for Detecting AI-Generated Imagescited by 2
  30. 2021DeepFakes: Detecting Forged and Synthetic Media Content Using Machine Learningcited by 1
  31. 2024Hierarchical Invariance for Robust and Interpretable Vision Tasks at Larger Scalescited by 1
  32. 2024Text Modality Oriented Image Feature Extraction for Detecting Diffusion-based DeepFakecited by 1
  33. 2024Herd Mentality in Augmentation -- Not a Good Idea! A Robust Multi-stage Approach towards Deepfake Detectioncited by 1
  34. 2026Towards High Fidelity Face Swapping: A Comprehensive Survey and New Benchmarkcited by 1
  35. 2026Revealing Artifacts via Noise Amplification: A Novel Perspective for AI-Generated Video Detectioncited by 1
  36. 2026Delving into the Temporal Challenges of Unified Video Protection Against Image-to-Video and Fine-Tuning-based Customizationcited by 1
  37. 2022Deep Fake Detection, Deterrence and Response: Challenges and Opportunitiescited by 0
  38. 2024Deepfake Detection and the Impact of Limited Computing Capabilitiescited by 0

50 most cited of 56 All 56 (JSON)