Data to 7 Oct 2026

Adversarial Deepfakes: Evaluating Vulnerability of Deepfake Detectors to Adversarial Examples

arXiv 2002.12749 ↗First posted 9 Feb 2020cs.CVcited by 66

Not on the map. Why?

Abstract (arXiv)

Recent advances in video manipulation techniques have made the generation of fake videos more accessible than ever before. Manipulated videos can fuel disinformation and reduce trust in media. Therefore detection of fake videos has garnered immense interest in academia and industry. Recently developed Deepfake detection methods rely on deep neural networks (DNNs) to distinguish AI-generated fake videos from real videos. In this work, we demonstrate that it is possible to bypass such detectors by adversarially modifying fake videos synthesized using existing Deepfake generation methods. We further demonstrate that our adversarial perturbations are robust to image and video compression codecs, making them a real-world threat. We present pipelines in both white-box and black-box attack scenarios that can fool DNN based Deepfake detectors into classifying fake videos as real.

Key facts. Cited by 66 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 Feb 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 16; 2023: 13; 2024: 14; 2025: 7; 2026: 6.

66 papers.

Sort:

By area:

2023Factuality Challenges in the Era of Large Language Modelscited by 125
2023Art and the science of generative AI: A deeper divecited by 93
2021KoDF: A Large-scale Korean DeepFake Detection Datasetcited by 80
2022Exploring Frequency Adversarial Attacks for Face Forgery Detectioncited by 45
2022Audio-Visual Person-of-Interest DeepFake Detectioncited by 43
2023SepMark: Deep Separable Watermarking for Unified Source Tracing and Deepfake Detectioncited by 43
2023Evading DeepFake Detectors via Adversarial Statistical Consistencycited by 37
2021Cross-modal Adversarial Reprogrammingcited by 34
2022FaceSigns: Semi-Fragile Neural Watermarks for Media Authentication and Countering Deepfakescited by 18
2021MagDR: Mask-guided Detection and Reconstruction for Defending Deepfakescited by 17
2022Digital and Physical Face Attacks: Reviewing and One Step Furthercited by 17
2022Making DeepFakes more spurious: evading deep face forgery detection via trace removal attackcited by 16

38 more

2021Deepfake Forensics via An Adversarial Gamecited by 15
2022Testing Human Ability To Detect Deepfake Images of Human Facescited by 15
2023Challenges and Remedies to Privacy and Security in AIGC: Exploring the Potential of Privacy Computing, Blockchain, and Beyondcited by 14
2024Generative AI Literacy: Twelve Defining Competenciescited by 13
2023AVA: Inconspicuous Attribute Variation-based Adversarial Attack bypassing DeepFake Detectioncited by 12
2024Vulnerabilities in AI-generated Image Detection: The Challenge of Adversarial Attackscited by 12
2022D4: Detection of Adversarial Diffusion Deepfakes Using Disjoint Ensemblescited by 11
2024Exploring the Adversarial Robustness of CLIP for AI-generated Image Detectioncited by 11
2022Generalizable Deepfake Detection with Phase-Based Motion Analysiscited by 10
2024Deepfake Media Generation and Detection in the Generative AI Era: A Survey and Outlookcited by 10
2021Where Do Deep Fakes Look? Synthetic Face Detection via Gaze Trackingcited by 9
2024XAI-Based Detection of Adversarial Attacks on Deepfake Detectorscited by 9
2023An adversarial attack approach for eXplainable AI evaluation on deepfake detection modelscited by 7
2021Understanding the Security of Deepfake Detectioncited by 6
2022Consistent Attack: Universal Adversarial Perturbation on Embodied Vision Navigationcited by 6
2023On the Vulnerability of DeepFake Detectors to Attacks Generated by Denoising Diffusion Modelscited by 6
2021Adversarially Perturbed Wavelet-based Morphed Face Generationcited by 4
2023Balancing Transparency and Risk: The Security and Privacy Risks of Open-Source Machine Learning Modelscited by 4
2024Is JPEG AI going to change image forensics?cited by 4
2025RAID: A Dataset for Testing the Adversarial Robustness of AI-Generated Image Detectorscited by 4
2022Publishing Efficient On-device Models Increases Adversarial Vulnerabilitycited by 3
2023Turn Fake into Real: Adversarial Head Turn Attacks Against Deepfake Detectioncited by 3
2025MS-GAGA: Metric-Selective Guided Adversarial Generation Attackcited by 3
2021Automated Deepfake Detectioncited by 2
2022Robust Deepfake On Unrestricted Media: Generation And Detectioncited by 2
2022Metamorphic Testing-based Adversarial Attack to Fool Deepfake Detectorscited by 2
2022ReFace: Real-time Adversarial Attacks on Face Recognition Systemscited by 2
2022FastStamp: Accelerating Neural Steganography and Digital Watermarking of Images on FPGAscited by 2
2023NetFlick: Adversarial Flickering Attacks on Deep Learning Based Video Compressioncited by 2
20242D-Malafide: Adversarial Attacks Against Face Deepfake Detection Systemscited by 2
2024Take Fake as Real: Realistic-like Robust Black-box Adversarial Attack to Evade AIGC Detectioncited by 2
2025Improving the Perturbation-Based Explanation of Deepfake Detectors Through the Use of Adversarially-Generated Samplescited by 2
2021DeepFakes: Detecting Forged and Synthetic Media Content Using Machine Learningcited by 1
2024Adversarially Robust Deepfake Detection via Adversarial Feature Similarity Learningcited by 1
2024GRACE: Graph-Regularized Attentive Convolutional Entanglement with Laplacian Smoothing for Robust DeepFake Video Detectioncited by 1
2025CAE-Net: Generalized Deepfake Image Detection using Convolution and Attention Mechanisms with Spatial and Frequency Domain Featurescited by 1
2025Realism to Deception: Investigating Deepfake Detectors Against Face Enhancementcited by 1
2025Frequency Bias Matters: Diving into Robust and Generalized Deep Image Forgery Detectioncited by 1

50 most cited of 66 All 66 (JSON)