mlsanityData to 7 Oct 2026

Fighting Fake News: Image Splice Detection via Learned Self-Consistency

arXiv 1805.04096 ↗First posted 10 May 2018cs.CVcited by 136

Not on the map. Why?

Abstract (arXiv)

Advances in photo editing and manipulation tools have made it significantly easier to create fake imagery. Learning to detect such manipulations, however, remains a challenging problem due to the lack of sufficient amounts of manipulated training data. In this paper, we propose a learning algorithm for detecting visual image manipulations that is trained only using a large dataset of real photographs. The algorithm uses the automatically recorded photo EXIF metadata as supervisory signal for training a model to determine whether an image is self-consistent -- that is, whether its content could have been produced by a single imaging pipeline. We apply this self-consistency model to the task of detecting and localizing image splices. The proposed method obtains state-of-the-art performance on several image forensics benchmarks, despite never seeing any manipulated images at training. That said, it is merely a step in the long quest for a truly general purpose visual forensics tool.

Key facts. Cited by 136 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 May 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 31; 2022: 25; 2023: 27; 2024: 24; 2025: 16; 2026: 13.

136 papers.

Sort:

By area:

  1. 2021PSCC-Net: Progressive Spatio-Channel Correlation Network for Image Manipulation Detection and Localizationcited by 133
  2. 2022Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detectioncited by 130
  3. 2022TruFor: Leveraging all-round clues for trustworthy image forgery detection and localizationcited by 130
  4. 2023Explicit Visual Prompting for Low-Level Structure Segmentationscited by 113
  5. 2021Face Forensics in the Wildcited by 87
  6. 2023Self-Supervised Video Forensics by Audio-Visual Anomaly Detectioncited by 84
  7. 2021Learning JPEG Compression Artifacts for Image Manipulation Detection and Localizationcited by 78
  8. 2022ObjectFormer for Image Manipulation Detection and Localizationcited by 78
  9. 2021Open-Domain, Content-based, Multi-modal Fact-checking of Out-of-Context Images via Online Resourcescited by 71
  10. 2021Making Images Real Again: A Comprehensive Survey on Deep Image Compositioncited by 63
  11. 2021Predicting Video with VQVAEcited by 61
  12. 2023Shadows Don't Lie and Lines Can't Bend! Generative Models don't know Projective Geometry...for nowcited by 61
38 more
  1. 2021BiHPF: Bilateral High-Pass Filters for Robust Deepfake Detectioncited by 60
  2. 2023Online Detection of AI-Generated Imagescited by 55
  3. 2023Multimodal Automated Fact-Checking: A Surveycited by 51
  4. 2024Community Forensics: Using Thousands of Generators to Train Fake Image Detectorscited by 50
  5. 2022Deepfake Network Architecture Attributioncited by 47
  6. 2021FReTAL: Generalizing Deepfake Detection using Knowledge Distillation and Representation Learningcited by 43
  7. 2023IML-ViT: Benchmarking Image Manipulation Localization by Vision Transformercited by 42
  8. 2024IMDL-BenCo: A Comprehensive Benchmark and Codebase for Image Manipulation Detection & Localizationcited by 42
  9. 2024Diffusion Facial Forgery Detectioncited by 41
  10. 2021CoReD: Generalizing Fake Media Detection with Continual Representation using Distillationcited by 37
  11. 2021Language-Driven Image Style Transfercited by 36
  12. 2021One Detector to Rule Them All: Towards a General Deepfake Attack Detection Frameworkcited by 33
  13. 2023Pixel-Inconsistency Modeling for Image Manipulation Localizationcited by 33
  14. 2021Self-Adversarial Training incorporating Forgery Attention for Image Forgery Localizationcited by 24
  15. 2023Weakly-supervised deepfake localization in diffusion-generated imagescited by 24
  16. 2023Towards Generic Image Manipulation Detection with Weakly-Supervised Self-Consistency Learningcited by 23
  17. 2023Pre-training-free Image Manipulation Localization through Non-Mutually Exclusive Contrastive Learningcited by 23
  18. 2024Mixture of Low-rank Experts for Transferable AI-Generated Image Detectioncited by 21
  19. 2021A Survey on Predicting the Factuality and the Bias of News Mediacited by 20
  20. 2022Defending Multimodal Fusion Models against Single-Source Adversariescited by 20
  21. 2021TAR: Generalized Forensic Framework to Detect Deepfakes using Weakly Supervised Learningcited by 19
  22. 2024GIM: A Million-scale Benchmark for Generative Image Manipulation Detection and Localizationcited by 19
  23. 2023EXIF as Language: Learning Cross-Modal Associations Between Images and Camera Metadatacited by 17
  24. 2024DeCLIP: Decoding CLIP representations for deepfake localizationcited by 17
  25. 2023Interpretable Multimodal Misinformation Detection with Logic Reasoningcited by 16
  26. 2024Exploring Multi-view Pixel Contrast for General and Robust Image Forgery Localizationcited by 15
  27. 2021Finding Facial Forgery Artifacts with Parts-Based Detectorscited by 14
  28. 2022Multi-modal Misinformation Detection: Approaches, Challenges and Opportunitiescited by 14
  29. 2024Multimodal Large Language Models to Support Real-World Fact-Checkingcited by 13
  30. 2024Multimodal Misinformation Detection by Learning from Synthetic Data with Multimodal LLMscited by 13
  31. 2022CFL-Net: Image Forgery Localization Using Contrastive Learningcited by 12
  32. 2023Deep Image Matting: A Comprehensive Surveycited by 12
  33. 2023Rethinking Image Forgery Detection via Soft Contrastive Learning and Unsupervised Clusteringcited by 12
  34. 2023Open Set Synthetic Image Source Attributioncited by 12
  35. 2021Deep Video Inpainting Detectioncited by 11
  36. 2022Comprint: Image Forgery Detection and Localization using Compression Fingerprintscited by 9
  37. 2022VideoFACT: Detecting Video Forgeries Using Attention, Scene Context, and Forensic Tracescited by 9
  38. 2023Deepfake detection by exploiting surface anomalies: the SurFake approachcited by 9

50 most cited of 136 All 136 (JSON)