DOCSEARCHbyAlgolia
Submit Docs

Awesome Deepfakes Detection

repository·main·Indexed 23 days ago

https://github.com/daisy-zhang/awesome-deepfakes-detection

A curated repository of resources for Deepfake Detection research. It includes categorized research papers from major conferences (CVPR, ICCV, ECCV, NeurIPS, ICLR, ICML, IJCAI, AAAI, ACM MM), video and image datasets such as Celeb-DF, DFDC, and ForgeryNet, detection tools, and historical competitions. The collection specifically focuses on detection methods, including spatiotemporal analysis, frequency-based detection, and generalization techniques.

Tokens
6K
Snippets
0
Records
36
Agent score
33%

What's inside awesome-deepfakes-detection

  1. Overview of Awesome Deepfakes Detection

    main

    This repository is a curated collection of resources related to Deepfake Detection, including datasets, tools, competitions, and research papers. It is intended for researchers and developers working on identifying manipulated media.

    Note: This repository focuses exclusively on detection. For resources related to Deepfake generation, refer to the Awesome Deepfakes repository.

  2. Research Survey Papers on Deepfake Detection

    main

    For a high-level understanding of the field, including definitions, performance metrics, standards, datasets, and benchmarks, refer to these survey papers:

    • Deepfake: Definitions, Performance Metrics and Standards, Datasets and Benchmarks, and a Meta-Review (arXiv 2022)
    • Deepfakes Generation and Detection: State-of-the-art, open challenges, countermeasures, and way forward (Applied Intelligence 2022)
    • DeepFake Detection for Human Face Images and Videos: A Survey (IEEE Access 2022)
    • Deepfake Detection: A Systematic Literature Review (IEEE Access 2022)
    • A Survey on Deepfake Video Detection (Iet Biometrics 2021)

  3. Generalization Focused Deepfake Detection Methods

    main

    These methods aim to improve the ability of detectors to work across different domains and forgery types. Key research includes:

    • Transcending Forgery Specificity with Latent Space Augmentation for Generalizable Deepfake Detection (CVPR 2024)
    • Rethinking the Up-Sampling Operations in CNN-based Generative Network for Generalizable Deepfake Detection (CVPR 2024) Github
    • Exploiting Style Latent Flows for Generalizing Video Deepfake Detection (CVPR 2024)
    • Controllable Guide-Space for Generalizable Face Forgery Detection (ICCV 2023)
    • Towards Understanding the Generalization of Deepfake Detectors from a Game-Theoretical View (ICCV 2023)
    • UCF: Uncovering Common Features for Generalizable Deepfake Detection (ICCV 2023)
    • Rethinking Domain Generalization for Face Anti-spoofing: Separability and Alignment (CVPR 2023) Github
    • Generalized Facial Manipulation Detection with Edge Region Feature Extraction (WACV 2022)
    • Supervised Contrastive Learning for Generalizable and Explainable DeepFakes Detection (WACV 2022) Github
    • Towards Generalizable Detection of Face Forgery via Self-Guided Model-Agnostic Learning (PRL 2022)
    • Learning to mask: Towards generalized face forgery detection (arXiv 2022)
    • FReTAL: Generalizing Deepfake Detection using Knowledge Distillation and Representation Learning (CVPR 2021)
    • Detection of Fake and Fraudulent Faces via Neural Memory Networks (TIFS 2021)
    • One detector to rule them all: Towards a general deepfake attack detection framework (Proceedings of the Web Conference 2021) Github
    • Supervised Contrastive Learning for Generalizable and Explainable DeepFakes Detection (WACV 2021) Github
    • Improving Generalization of Deepfake Detection with Domain Adaptive Batch Normalization (Proceedings of the 1st International Workshop on Adversarial Learning for Multimedia 2021)
    • FeatureTransfer: Unsupervised Domain Adaptation for Cross-Domain Deepfake Detection (Security and Communication Networks 2021)
    • Training Strategies and Data Augmentations in CNN-based DeepFake Video Detection (WIFS 2020)
    • Improved Generalizability of Deep-Fakes Detection Using Transfer Learning Based CNN Framework (ICICT 2020)
    • ForensicTransfer: Weakly-supervised Domain Adaptation for Forgery Detection (arXiv 2018)

  4. Research papers from ICCV

    main
    A collection of deepfake detection research papers published at the International Conference on Computer Vision (ICCV) from 2019 to 2023. Key research areas include game-theoretical views of generalization, thumbnail layout for video detection, identity-aware detection, and GAN fingerprinting.

  6. Research papers on Deepfake Detection in Real Scenarios

    main

    Research focused on the practical application and vulnerabilities of deepfake detection in real-world environments:

    • Social Media & Online Networks: Detecting forgery in images transmitted over social networks and identifying deepfake sources (DeSI).
    • Celebrity Impersonation: Evaluating how deepfakes impact face recognition and verification APIs.
    • Authentication Security: Investigating the security of facial liveness verification and preventing deepfake attacks on speaker authentication (using lip movement analysis).
    • Open Platforms: Tools like DeepFake-o-meter for open deepfake detection.
    • Privacy & Anonymization: Using deepfakes for social media anonymization.

  7. Spatiotemporal Based Deepfake Detection Methods

    main

    These methods focus on detecting temporal inconsistencies and spatial-temporal features in videos. Key research includes:

    • TALL: Thumbnail Layout for Deepfake Video Detection (ICCV 2023) Github
    • Hierarchical Contrastive Inconsistency Learning for Deepfake Video Detection (ECCV 2022)
    • Region-Aware Temporal Inconsistency Learning for DeepFake Video Detection (IJCAI 2022)
    • FInfer: Frame Inference-based Deepfake Detection for High-Visual-Quality Videos (AAAI 2022)
    • Delving into the Local: Dynamic Inconsistency Learning for DeepFake Video Detection (AAAI 2022)
    • Deepfake video detection with spatiotemporal dropout transformer (ACM MM 2022)
    • Exploring Complementarity of Global and Local Spatiotemporal Information for Fake Face Video Detection (ICASSP 2022)
    • Face Forgery Detection Based on Facial Region Displacement Trajectory Series (arXiv 2022)
    • Do You Really Mean That? Content Driven Audio-Visual Deepfake Dataset and Multimodal Method for Temporal Forgery Localization (arXiv 2022)
    • Exploring Temporal Coherence for More General Video Face Forgery Detection (ICCV 2021)
    • Detecting Deepfake Videos with Temporal Dropout 3DCNN (IJCAI 2021)
    • Video Transformer for Deepfake Detection with Incremental Learning (ACM MM 2021)
    • FSSPOTTER: Spotting Face-Swapped Video by Spatial and Temporal Clues (ICME 2020)
    • Deepfake Video Detection Based on Spatial, Spectral, and Temporal Inconsistencies Using Multimodal Deep Learning (AIPR 2020)

  10. Research papers on Deepfake Localization

    main
    This category covers methods for not just detecting deepfakes, but specifically locating the manipulated regions (artifacts) within an image or video. Techniques include localized artifact attention networks (LAA-Net), hierarchical fine-grained detection, and spatial-temporal feature exploration.