Awesome
Awesome Comprehensive Deepfake Detection
This repository provides a comprehensive investigation of advanced single-modal and multi-modal deepfake detection elaborated in the following survey.
<p align="center" style="font-size:20px;"> <h2>Evolving from Single-modal to Multi-modal Facial Deepfake Detection: A Survey <a href="https://arxiv.org/pdf/2406.06965"><img src='https://img.shields.io/badge/arXiv-PDF-red?style=flat&logo=arXiv&logoColor=red' alt='arXiv PDF'></a> </h2> </p> <p align="center"> <a href="https://pinglmlcv.github.io/pingliu264/">Ping Liu<sup>1</sup></a> , Qiqi Tao<sup>2</sup> , <a href="https://joeyzhouty.github.io/">Joey Tianyi Zhou<sup>2,3</sup></a> </p> <p align="center"> <sup>1</sup><a href="https://www.unr.edu/cse">University of Nevada, Reno</a><br> <sup>2</sup><a href="https://www.a-star.edu.sg/cfar/home">Centre for Frontier AI Research (CFAR), A*STAR</a><br> <sup>3</sup><a href="https://www.catos.sg/"> Centre for Advanced Technologies in Online Safety (CATOS)</a> </p>If you believe there are additional works that should be included in our list, please do not hesitate to send us an email (pingl@unr.edu/tao.qiqi@outlook.com/zhouty@cfar.a-star.edu.sg) or raise an issue. Your suggestions and comments are invaluable to ensuring the completeness and accuracy of our resource.
Content
- Relevant Surveys
- Facial Deepfake Datasets
- Single-modal (Visual) Deepfake Detection
- Multi-modal Deepfake Detection
- Trustworthy Deepfake Detection
Relevant Surveys
Deepfake/AIGC Generation and Detection
[arxiv 2024] Deepfake Generation and Detection: A Benchmark and Survey Paper Project
[arxiv 2024] Detecting Multimedia Generated by Large AI Models: A Survey Paper Project
[ECAI 2023] GAN-generated Faces Detection: A Survey and New Perspectives Paper
[NeurIPS 2023] DeepfakeBench: A Comprehensive Benchmark of Deepfake Detection Paper Project
[arxiv 2023] Deepfake detection: A comprehensive study from the reliability perspective Paper
[IJCV 2022] Countering Malicious DeepFakes: Survey, Battleground, and Horizon Paper Project
Multi-modal Fact-checking
[EMNLP 2023] Multimodal automated fact-checking: A survey Paper
Facial Deepfake Datasets
Single-modal GAN-generated Datasets
Single-modal Diffusion-generated Datasets
Dataset | Year | Task | Manipulated Modality | # of real images | # of fake images | Paper | Link |
---|---|---|---|---|---|---|---|
DeepFakeFace | 2023 | Classification | Visual | 30,000 | 90,000 | Robustness and Generalizability of Deepfake Detection: A Study with Diffusion Models | Download |
DiFF | 2024 | Classification | Visual | 23,661 | 537,466 | Diffusion Facial Forgery Detection | Download |
DiffusionFace | 2024 | Classification | Visual | 30,000 | 600,000 | DiffusionFace: Towards a Comprehensive Dataset for Diffusion-Based Face Forgery Analysis | Download |
DiffusionDB-Face | 2024 | Classification | Visual | 94,120 | 24,794 | Diffusion Deepfake | Download |
JourneyDB-Face | 2024 | Classification | Visual | 94,120 | 87,833 | Diffusion Deepfake | Download |
Multi-modal Audio-Visual Datasets
Multi-modal Text-Visual Datasets
Dataset | Year | Task | Manipulated Modality | # of real image-text pairs | # of fake image-text pairs | Paper | Link |
---|---|---|---|---|---|---|---|
DGM4 | 2023 | Classification & Spatial Grounding & Text Grounding | Visual & Text | 77,426 | 152,574 | DGM4: Detecting and Grounding Multi-Modal Media Manipulation and Beyond | Download |
Single-modal (Visual) Deepfake Detection
Passive Detection
Naive Detection
Visual Artifacts
- [CVPR 2024] Rethinking the Up-Sampling Operations in CNN-based Generative Network for Generalizable Deepfake Detection Paper
- [CVPR 2024] LAA-Net: Localized Artifact Attention Network for Quality-Agnostic and Generalizable Deepfake Detection Paper
- [arXiv 2024] Data-Independent Operator: A Training-Free Artifact Representation Extractor for Generalizable Deepfake Detection Paper
- [arXiv 2024] A Single Simple Patch is All You Need for AI-generated Image Detection Paper
- [arXiv 2024] GenFace: A Large-Scale ed Face Forgery Benchmark and Cross Appearance-Edge Learning Paper
- [TMM 2023] GLFF: Global and Local Feature Fusion for AI-synthesized Image Detection Paper
- [CVPRW 2023] Intriguing properties of synthetic images: from generative adversarial networks to diffusion models Paper
- [arXiv 2023] Diffusion Noise Feature: Accurate and Fast Generated Image Detection Paper
- [CVPR 2021] Multi-attentional Deepfake Detection Paper
- [CVPR 2020] Global Texture Enhancement for Fake Face Detection In the Wild Paper
- [ICCV 2019] FaceForensics++: Learning to Detect Manipulated Facial Images Paper
- [WIFS 2018] Mesonet: a compact facial video forgery detection network Paper
Consistencies-based
- [arXiv 2024] Generalizing Deepfake Video Detection with Plug-and-Play: Video-Level Blending and Spatiotemporal Adapter Tuning Paper
- [arXiv 2024] UniForensics: Face Forgery Detection via General Facial Representation Paper
- [arXiv 2024] Learning Natural Representation for Face Forgery Video Detection Paper
- [IJCV 2024] Learning Spatiotemporal Inconsistency via Thumbnail Layout for Face Deepfake Detection Paper
- [CVPR 2024] Exploiting Style Latent Flows for Generalizing Deepfake Video Detection Paper
- [arxiv 2024] Compressed Deepfake Video Detection Based on 3D Spatiotemporal Trajectories Paper
- [AAAI 2023] Noise based deepfake detection via multi-head relative-interaction Paper
- [ICCV 2023] TALL: Thumbnail Layout for Deepfake Video Detection Paper
- [CVPR 2023] AltFreezing for More General Video Face Forgery Detection Paper
- [TCSVT 2023] MRE-Net: Multi-Rate Excitation Network for Deepfake Video Detection Paper
- [WACV 2023] TI2Net: Temporal Identity Inconsistency Network for Deepfake Detection Paper
- [ACM MM Asia 2022] Latent pattern sensing: Deepfake video detection via predictive representation learning Paper
- [CVPR 2021] Lips don’t lie: A generalisable and robust approach to face forgery detection Paper
- [ICCV 2021] Exploring Temporal Coherence for More General Video Face Forgery Detection Paper
- [ACM MM 2020] DeepRhythm: Exposing DeepFakes with Attentional Visual Heartbeat Rhythms Paper
- [WIFS 2018] In Ictu Oculi: Exposing AI Created Fake Videos by Detecting Eye Blinking Paper
Advanced Detection
Input Level
Data Augmentation
- [arXiv 2024] Towards General Deepfake Detection with Dynamic Curriculum Paper
- [ECCV 2024] Fake It till You Make It: Curricular Dynamic Forgery Augmentations towards General Deepfake Detection Paper
- [arXiv 2024] Can We Leave Deepfake Data Behind in Training Deepfake Detector? Paper
- [arXiv 2024] ED4: Explicit Data-level Debiasing for Deepfake Detection Paper
- [arXiv 2024] FSBI: Deepfakes Detection with Frequency Enhanced Self-Blended Images Paper
- [arXiv 2024] FreqBlender: Enhancing DeepFake Detection by Blending Frequency Knowledge Paper
- [ICCV 2023] SeeABLE: Soft Discrepancies and Bounded Contrastive Learning for Exposing Deepfakes Paper
- [arXiv 2023] Transcending Forgery Specificity with Latent Space Augmentation for Generalizable Deepfake Detection Paper
- [CVPR 2022] Detecting Deepfakes with Self-Blended Images Paper
- [CVPR 2022] Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detection Paper
- [CVPR 2021] Representative Forgery Mining for Fake Face Detecti Paper
- [ICCV 2021] Learning Self-Consistency for Deepfake Detection Paper
Frequency-space Based
- [arXiv 2024] HARNESSING WAVELET TRANSFORMATIONS FOR GENERALIZABLE DEEPFAKE FORGERY DETECTION Paper
- [arXiv 2024] Multiple Contexts and Frequencies Aggregation Network for Deepfake Detection Paper
- [AAAI 2024] Frequency-Aware Deepfake Detection: Improving Generalizability through Frequency Space Learning Paper
- [ICASSP 2024] Frequency Masking for Universal Deepfake Detection Paper
- [CVPR 2023] Dynamic Graph Learning with Content-guided Spatial-Frequency Relation Reasoning for Deepfake Detection Paper
- [AAAI 2022] FrePGAN: Robust Deepfake Detection Using Frequency-level Perturbations Paper
- [AAAI 2022] ADD: Frequency Attention and Multi-View based Knowledge Distillation to Detect Low-Quality Compressed Deepfake Images Paper
- [CVPR 2021] Spatial-Phase Shallow Learning: Rethinking Face Forgery Detection in Frequency Domain Paper
- [CVPR 2021] Generalizing Face Forgery Detection with High-frequency Features Paper
- [CVPR 2021] Frequency-aware Discriminative Feature Learning Supervised by Single-Center Loss for Face Forgery Detection Paper
- [AAAI 2021] Local Relation Learning for Face Forgery Detection Paper
- [ECCV 2020] Thinking in Frequency: Face Forgery Detection by Mining Frequency-aware Clues Paper
Model Level
Transformer-based
- [TMM 2024] DIP: Diffusion Learning of Inconsistency Pattern for General DeepFake Detection Paper
- [arXiv 2024] FakeFormer: Efficient Vulnerability-Driven Transformers for Generalisable Deepfake Detection Paper
- [arXiv 2024] HARNESSING WAVELET TRANSFORMATIONS FOR GENERALIZABLE DEEPFAKE FORGERY DETECTION Paper
- [arXiv 2024] Face Forgery Detection with Elaborate Backbone Paper
- [arXiv 2024] Standing on the Shoulders of Giants: Reprogramming Visual-Language Model for General Deepfake Detection Paper
- [arXiv 2024] Guided and Fused: Efficient Frozen CLIP-ViT with Feature Guidance and Multi-Stage Feature Fusion for Generalizable Deepfake Detection Paper
- [arXiv 2024] Open-Set Deepfake Detection: A Parameter-Efficient Adaptation Method with Forgery Style Mixture Paper
- [arXiv 2024] A Timely Survey on Vision Transformer for Deepfake Detection Paper
- [arXiv 2024] Exploring Self-Supervised Vision Transformers for Deepfake Detection: A Comparative Analysis Paper
- [arXiv 2024] Mixture of Low-rank Experts for Transferable AI-Generated Image Detection Paper
- [arXiv 2024] MoE-FFD: Mixture of Experts for Generalized and Parameter-Efficient Face Forgery Detection Paper
- [CVPR 2023] AUNet: Learning Relations Between Action Units for Face Forgery Detection Paper
- [ACM MM 2023] UMMAFormer: A Universal Multimodal-adaptive Transformer Framework for Temporal Forgery Localization Paper
- [ICCVW 2023] Undercover Deepfakes: Detecting Fake Segments in Video Paper
- [arXiv 2023] DeepFake-Adapter: Dual-Level Adapter for DeepFake Detection Paper
- [MIPR 2023] Enhancing General Face Forgery Detection via Vision Transformer with Low-Rank Adaptation Paper
VLM-based
- [arXiv 2024] ForgeryGPT: Multimodal Large Language Model For Explainable Image Forgery Detection and Localization Paper
- [ACCV 2024] DPL: Cross-quality DeepFake Detection via Dual Progressive Learning Paper
- [WACV 2025] DeCLIP: Decoding CLIP representations for deepfake localization Paper
- [arXiv 2024] X2-DFD: A FRAMEWORK FOR EXPLAINABLE AND EXTENDABLE DEEPFAKE DETECTION Paper
- [arXiv 2024] MFCLIP: Multi-modal Fine-grained CLIP for Generalizable Diffusion Face Forgery Detection Paper
- [arXiv 2024] FFAA: Multimodal Large Language Model based Explainable Open-World Face Forgery Analysis Assistant Paper
- [arXiv 2024] C2P-CLIP: Injecting Category Common Prompt in CLIP to Enhance Generalization in Deepfake Detection Paper
- [arXiv 2024] GM-DF: Generalized Multi-Scenario Deepfake Detection Paper
- [arXiv 2024] Towards More General Video-based Deepfake Detection through Facial Feature Guided Adaptation for Foundation Model Paper
- [arXiv 2024] FakeBench: Uncover the Achilles' Heels of Fake Images with Large Multimodal Models Paper
- [CVPR Workshop 2024] Can ChatGPT Detect DeepFakes? A Study of Using Multimodal Large Language Models for Media Forensics Paper
- [arXiv 2024] SHIELD: An Evaluation Benchmark for Face Spoofing and Forgery Detection with Multimodal Large Language Models Paper
- [arXiv 2024] Common Sense Reasoning for Deep Fake Detection Paper
- [ACM ICMRW 2024] Towards Quantitative Evaluation of Explainable AI Methods for Deepfake Detection Paper
- [arxiv 2023] Forgery-aware Adaptive Vision Transformer for Face Forgery Detection Paper
- [arXiv 2023] Towards General Visual-Linguistic Face Forgery Detection Paper
Learning Level
Advanced Loss
- [ToMM 2024] Domain-invariant and Patch-discriminative Feature Learning for General Deepfake Detection Paper
- [ICME 2023] Domain-Invariant Feature Learning for General Face Forgery Detection Paper
- [ICDM 2023] Concentric Ring Loss for Face Forgery Detection Paper
Disentangled Representation
- [arXiv 2024] Capture Artifacts via Progressive Disentangling and Purifying Blended Identities for Deepfake Detection Paper
- [CVPR 2024] Preserving Fairness Generalization in Deepfake Detection Paper
- [arXiv 2024] Decoupling Forgery Semantics for Generalizable Deepfake Detection Paper
- [arXiv 2023] Improving Cross-dataset Deepfake Detection with Deep Information Decomposition Paper
- [ICCV 2023] UCF: Uncovering Common Features for Generalizable Deepfake Detection Paper
- [ECCV 2022] Exploring Disentangled Content Information for Face Forgery Detection Paper
Reconstruction
- [CVPR 2023] MARLIN: Masked Autoencoder for facial video Representation LearnINg Paper
- [CVPR 2022] End-to-End Reconstruction-Classification Learning for Face Forgery Detection Paper
- [IJCAI 2021] Beyond the Spectrum: Detecting Deepfakes via Re-Synthesis Paper
- [CVPRW 2020] OC-FakeDect: Classifying Deepfakes Using One-class Variational Autoencoder Paper
Manipulation Localization
- [CVPR 2024] EditGuard: Versatile Image Watermarking for Tamper Localization and Copyright Protection Paper
- [WACV 2024] Weakly-supervised deepfake localization in diffusion-generated images Paper
- [arXiv 2024] Delocate: Detection and Localization for Deepfake Videos with Randomly-Located Tampered Traces Paper
- [CVPR 2023] MaLP: Manipulation Localization Using a Proactive Scheme Paper
- [CVPR 2023] Implicit Identity Leakage: The Stumbling Block to Improving Deepfake Detection Generalization Paper
- [ACM MM 2023] Locate and Verify: A Two-Stream Network for Improved Deepfake Detection Paper
- [CVPR 2020] Face X-ray for More General Face Forgery Detection Paper
- [CVPR 2020] On the Detection of Digital Face Manipulation Paper
Identity Discrepancy
- [NeurIPS 2024] DiffusionFake: Enhancing Generalization in Deepfake Detection via Guided Stable Diffusion Paper
- [CVPR 2023] Implicit Identity Driven Deepfake Face Swapping Detection Paper
- [CVPR 2022] Protecting Celebrities from DeepFake with Identity Consistency Transformer Paper
- [TPAMI 2021] DeepFake Detection Based on Discrepancies Between Faces and Their Context Paper
- [ICCV 2021] ID-Reveal: Identity-aware DeepFake Video Detection Paper
Knowledge Distillation
- [arXiv 2023] DomainForensics: Exposing Face Forgery across Domains via Bi-directional Adaptation Paper
- [AAAI 2022] ADD: Frequency Attention and Multi-View based Knowledge Distillation to Detect Low-Quality Compressed Deepfake Images Paper
- [ACM MM 2021] CoReD: Generalizing Fake Media Detection with Continual Representation using Distillation Paper
- [CVPRW 2021] FReTAL: Generalizing Deepfake Detection using Knowledge Distillation and Representation Learning Paper
- [Journal of Mathematical Imaging and Vision 2015] Sliced and Radon Wasserstein Barycenters of Measures Paper
Fine-grained Prediction
- [arXiv 2024] Semantics-Oriented Multitask Learning for DeepFake Detection: A Joint Embedding Approach Paper
- [ToMM 2024] Mastering Deepfake Detection: A Cutting-Edge Approach to Distinguish GAN and Diffusion-Model Images Paper
- [CVPR 2023] Hierarchical Fine-Grained Image Forgery Detection and Localization Paper
- [ICCV 2023] Controllable Guide-Space for Generalizable Face Forgery Detection Paper
Diffusion Model Detection
- [arXiv 2024] On the Effectiveness of Dataset Alignment for Fake Image Detection Paper
- [CVPR 2024] LaRE^2: Latent Reconstruction Error Based Method for Diffusion-Generated Image Detection Paper
- [VISAPP 2024] Towards the Detection of Diffusion Model Deepfakes Paper
- [arXiv 2024] Diffusion Facial Forgery Detection Paper
- [ICCV 2023] DIRE for Diffusion-Generated Image Detection Paper
- [ICASSP 2023] On the detection of synthetic images generated by diffusion models Paper
- [ICCVW 2023] Detecting Images Generated by Deep Diffusion Models using their Local Intrinsic Dimensionality Paper
- [ICMLW 2023] Exposing the Fake: Effective Diffusion-Generated Images Detection Paper
Sequential Deepfake Detection
- [ECCV 2022] Detecting and Recovering Sequential DeepFake Manipulation Paper
- [arXiv 2023] Robust Sequential DeepFake Detection Paper
- [CVPR 2024] Contrastive Learning for DeepFake Classification and Localization via Multi-Label Ranking Paper
- [TIFS 2024] Multi-Collaboration and Multi-Supervision Network for Sequential Deepfake Detection Resources Paper
- [Transactions on Consumer Electronics 2024] Detecting Sequential Deepfake Manipulation via Spectral With Pyramid Attention in Consumer IoT Paper
Proactive Detection
Proactive Methods for GANs
- [arXiv 2024] ID-Guard: A Universal Framework for Combating Facial Manipulation via Breaking Identification Paper
- [IJCAI 2024] Are Watermarks Bugs for Deepfake Detectors? Rethinking Proactive Forensics Paper
- [TIFS 2024] Dual Defense: Adversarial, Traceable, and Invisible Robust Watermarking against Face Swapping Paper
- [CVPR 2023] MaLP: Manipulation Localization Using a Proactive Scheme Paper
- [ACM MM 2023] SepMark: Deep Separable Watermarking for Unified Source Tracing and Deepfake Detection Paper
- [arXiv 2023] Feature Extraction Matters More: Universal Deepfake Disruption through Attacking Ensemble Feature Extractors Paper
- [arXiv 2023] Robust Identity Perceptual Watermark Against Deepfake Face Swapping Paper
- [CVPR 2022] Proactive Image Manipulation Detection Paper
- [ICLR 2022] Responsible Disclosure of Generative Models Using Scalable Fingerprinting Paper
- [ECCV 2022] TAFIM: Targeted Adversarial Attacks against Facial Image Manipulations Paper
- [AAAI 2022] CMUA-Watermark: A Cross-Model Universal Adversarial Watermark for Combating Deepfake Paper
- [IJCAI 2022] Anti-Forgery: Towards a Stealthy and Robust DeepFake Disruption Attack via Adversarial Perceptual-aware Perturbations Paper
- [AAAI 2021] Initiative Defense against Facial Manipulation Paper
- [CVPRW 2020] Disrupting Deepfakes: Adversarial Attacks Against Conditional Image Translation Networks and Facial Manipulation Systems Paper
- [WACVW 2020] Disrupting Image-Translation-Based DeepFake Algorithms with Adversarial Attacks Paper
Proactive Methods for Diffusion Models
- [ICLR 2024] DIAGNOSIS: Detecting Unauthorized Data Usages in Text-to-image Diffusion Models Paper
- [NeurIPSW 2024] DiffusionShield: A Watermark for Data Copyright Protection against Generative Diffusion Models Paper
- [ICCV 2023] The Stable Signature: Rooting Watermarks in Latent Diffusion Models Paper
- [TPS-ISA 2023] Invisible Watermarking for Audio Generation Diffusion Models Paper
- [arXiv 2023] A Recipe for Watermarking Diffusion Models Paper
- [arXiv 2023] LEAT: Towards Robust Deepfake Disruption in Real-World Scenarios via Latent Ensemble Attack Paper
Multi-modal Deepfake Detection
Audio-Visual Deepfake Detection
Independent Learning
- [Applied Soft Computing 2023] AVFakeNet: A unified end-to-end Dense Swin deep learning model for audio–visual deepfakes detection Paper
- [APSIPA ASC 2022] Multimodal Forgery Detection Using Ensemble Learning Paper
- [ICCV 2021] Joint Audio-Visual Deepfake Detection Paper
- [ACM MMW 2021] Evaluation of an Audio-Video Multimodal Deepfake Dataset using Unimodal and Multimodal Detectors Paper
Joint Learning
Intermediate Fusion
Cross-Attention
- [BMVC 2024] Detecting Audio-Visual Deepfakes with Fine-Grained Inconsistencies Paper
- [arXiv 2024] Contextual Cross-Modal Attention for Audio-Visual Deepfake Detection and Localization Paper
- [TIFS 2023] AVoiD-DF: Audio-Visual Joint Learning for Detecting Deepfake Paper
- [arXiv 2022] An Audio-Visual Attention Based Multimodal Network for Fake Talking Face Videos Detection Paper
- [ICCV 2021] Joint Audio-Visual Deepfake Detection Paper
Late Fusion
Concatenation & Addition
- [arXiv 2024] Integrating Audio-Visual Features for Multimodal Deepfake Detection Paper
- [arXiv 2024] AVT2-DWF: Improving Deepfake Detection with Audio-Visual Fusion and Dynamic Weighting Strategies Paper
- [Image Communication 2023] Magnifying multimodal forgery clues for Deepfake detection Paper
- [arXiv 2023] DF-TransFusion: Multimodal Deepfake Detection via Lip-Audio Cross-Attention and Facial Self-Attention Paper
- [DICTA 2022] Do You Really Mean That? Content Driven Audio-Visual Deepfake Dataset and Multimodal Method for Temporal Forgery Localization Paper
- [APSIPA ASC 2022] Multimodal Forgery Detection Using Ensemble Learning Paper
- [ACM MMW 2021] Evaluation of an Audio-Video Multimodal Deepfake Dataset using Unimodal and Multimodal Detectors Paper
Attention
- [ICASSP 2024] Cross-Modality and Within-Modality Regularization for Audio-Visual DeepFake Detection Paper
- [arXiv 2024] AVT2-DWF: Improving Deepfake Detection with Audio-Visual Fusion and Dynamic Weighting Strategies Paper
- [arXiv 2023] MIS-AVoiDD: Modality Invariant and Specific Representation for Audio-Visual Deepfake Detection Paper
MLP Mixer Layer
- [CVPRW 2023] Multimodaltrace: Deepfake Detection using Audiovisual Representation Learning Paper
Multi-task Strategy
- [ICME 2024] Explicit Correlation Learning for Generalizable Cross-Modal Deepfake Detection Paper
- [TIFS 2023] AVoiD-DF: Audio-Visual Joint Learning for Detecting Deepfake Paper
- [CVPRW 2023] Multimodaltrace: Deepfake Detection using Audiovisual Representation Learning Paper
- [arXiv 2024] Integrating Audio-Visual Features for Multimodal Deepfake Detection Paper
- [ICCV 2021] Joint Audio-Visual Deepfake Detection Paper
Regularization
- [ICASSP 2024] Cross-Modality and Within-Modality Regularization for Audio-Visual DeepFake Detection Paper
- [TIFS 2023] AVoiD-DF: Audio-Visual Joint Learning for Detecting Deepfake Paper
- [Image Communication 2023] Magnifying multimodal forgery clues for Deepfake detection Paper
- [arXiv 2023] MIS-AVoiDD: Modality Invariant and Specific Representation for Audio-Visual Deepfake Detection Paper
Matching-based Learning
- [ICIP 2024] Statistics-aware Audio-visual Deepfake Detector Paper
- [ToMM 2023] Voice-Face Homogeneity Tells Deepfake Paper
- [arXiv 2023] Unsupervised Multimodal Deepfake Detection Using Intra- and Cross-Modal Inconsistencies Paper
Others
- [CVPR 2024] AVFF: Audio-Visual Feature Fusion for Video Deepfake Detection Paper
- [CVPR 2023] Self-Supervised Video Forensics by Audio-Visual Anomaly Detection Paper
- [ToMM 2023] Multimodal Neurosymbolic Approach for Explainable Deepfake Detection Paper
- [TCSVT 2023] PVASS-MDD: Predictive Visual-audio Alignment Self-supervision for Multimodal Deepfake Detection Paper
- [CVPRW 2023] Audio-Visual Person-of-Interest DeepFake Detection Paper
Visual-Text Deepfake Detection
- [TPAMI 2024] Detecting and Grounding Multi-Modal Media Manipulation and Beyond Paper
- [ICASSP 2024] Exploiting Modality-Specific Features For Multi-Modal Manipulation Detection And Grounding Paper
- [ICME 2024] Counterfactual Explanations for Face Forgery Detection via Adversarial Removal of Artifacts Paper
- [arXiv 2023] Unified Frequency-Assisted Framework for Detecting and Grounding Multi-Modal Manipulation Paper
- [CVPR 2023] Detecting and Grounding Multi-Modal Media Manipulation Paper
Challenge
- [ACM MM 2024] 1M-Deepfakes Detection Challenge Paper
Trustworthy Deepfake Detection
Adversarial Attack
- [ECCVW 2024] Exploring Strengths and Weaknesses of Super-Resolution Attack in Deepfake Detection Paper
- [arXiv 2024] Adversarial Magnification to Deceive Deepfake Detection through Super Resolution Paper
- [AAAI 2024] TraceEvader: Making DeepFakes More Untraceable via Evading the Forgery Model Attribution Paper
- [ICASSP 2024] AdvShadow: Evading DeepFake Detection via Adversarial Shadow Attack Paper
- [CVPR 2023] Evading Forensic Classifiers with Attribute-Conditioned Adversarial Faces Paper
- [ICCV 2023] Frequency-aware GAN for Adversarial Manipulation Generation Paper
- [TCSVT 2023] Dodging DeepFake Detection via Implicit Spatial-Domain Notch Filtering Paper
- [arXiv 2023] Exploring Decision-based Black-box Attacks on Face Forgery Detection Paper
- [arXiv 2023] Exploring Decision-based Black-box Attacks on Face Forgery Detection Paper
- [arXiv 2023] AVA: Inconspicuous Attribute Variation-based Adversarial Attack bypassing DeepFake Detection Paper
- [arXiv 2023] Turn Fake into Real: Adversarial Head Turn Attacks Against Deepfake Detection Paper
- [CVPR 2022] Exploring Frequency Adversarial Attacks for Face Forgery Detection Paper
- [WDCW 2022] Evaluating Robustness of Sequence-based Deepfake Detector Models by Adversarial Perturbation Paper
- [ICIP 2021] Imperceptible Adversarial Examples for Fake Image Detection Paper
- [CVPRW2021] Adversarial Threats to DeepFake Detection: A Practical Perspective Paper
- [WACV 2021] Adversarial Deepfakes: Evaluating Vulnerability of Deepfake Detectors to Adversarial Examples Paper
- [CVPRW 2020] Evading Deepfake-Image Detectors with White- and Black-Box Attacks Paper
- [ECCVW 2020] Adversarial Attack on Deepfake Detection Using RL Based Texture Patches Paper
- [IJCNN 2020] Adversarial Perturbations Fool Deepfake Detectors Paper
Backdoor Attack
- [ICLR 2024] Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection Paper
- [arXiv 2024] Is It Possible to Backdoor Face Forgery Detection with Natural Triggers? Paper
- [BigDIA 2023] Real is not True: Backdoor Attacks Against Deepfake Detection Paper
Discrepancy Minimization
- [AAAI 2024] Spectrum Translation for Refinement of Image Generation (STIG) Based on Contrastive Learning and Spectral Filter Profile Paper
- [WACVW 2024] On the Vulnerability of DeepFake Detectors to Attacks Generated by Denoising Diffusion Models Paper
- [CVPR 2023] Evading DeepFake Detectors via Adversarial Statistical Consistency Paper
- [IEEE Transactions on Dependable and Secure Computing 2023] Making DeepFakes More Spurious: Evading Deep Face Forgery Detection via Trace Removal Attack Paper
- [CVPR 2022] Think Twice Before Detecting GAN-generated Fake Images from their Spectral Domain Imprints Paper
- [ACM MM 2022] Defeating DeepFakes via Adversarial Visual Reconstruction Paper
- [CVPR 2021] Exploring Adversarial Fake Images on Face Manifold Paper
- [ACM MM 2020] FakePolisher: Making DeepFakes More Detection-Evasive by Shallow Reconstruction Paper
- [arXiv 2020] FakeRetouch: Evading DeepFakes Detection via the Guidance of Deliberate Noise Paper
Defense Strategies
- [WACV 2024] D4: Detection of Adversarial Diffusion Deepfakes Using Disjoint Ensembles Paper
- [TIFS 2024] DF-RAP: A Robust Adversarial Perturbation for Defending Against Deepfakes in Real-World Social Network Scenarios Paper
- [ICMM 2024] Adversarially Robust Deepfake Detection via Adversarial Feature Similarity Learning Paper
- [arXiv 2024] XAI-Based Detection of Adversarial Attacks on Deepfake Detectors Paper
- [FG 2023] FaceGuard: A Self-Supervised Defense Against Adversarial Face Images Paper
- [IEEE Symposium Series on Computational Intelligence 2022] Adversarially Robust Deepfake Video Detection Paper
- [Journal of Electronic Imaging 2021] EnsembleDet: ensembling against adversarial attack on deepfake detection Paper
- [arXiv 2021] Adversarially robust deepfake media detection using fused convolutional neural network predictions Paper
Efficient Deepfake Detection
- [arXiv 2024] Real-Time Deepfake Detection in the Real-World Paper
- [CVPR 2024 DFAD Workshop] Faster than lies: Real-time deepfake detection using binary neural networks Paper
Privacy-aware Deepfake Detection
- [arXiv 2024] Federated Face Forgery Detection Learning with Personalized Representation Paper
- [TIFS 2023] FedForgery: generalized face forgery detection with residual federated learning Paper
- [2022 IEEE 24th International Workshop on Multimedia Signal Processing (MMSP)] Deepfake Detection with Data Privacy Protection Paper