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

arXiv: https://arxiv.org/abs/1805.04096 · HTML: https://mlsanity.com/paper/1805.04096/

## Key facts

- Cited by 136 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 May 2018.

## Built on by (most cited first, 30 of 136)

- [PSCC-Net: Progressive Spatio-Channel Correlation Network for Image Manipulation Detection and Localization](https://mlsanity.com/paper/2103.10596/) (2021)
- [Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detection](https://mlsanity.com/paper/2201.07131/) (2022)
- [TruFor: Leveraging all-round clues for trustworthy image forgery detection and localization](https://mlsanity.com/paper/2212.10957/) (2022)
- [Explicit Visual Prompting for Low-Level Structure Segmentations](https://mlsanity.com/paper/2303.10883/) (2023)
- [Face Forensics in the Wild](https://mlsanity.com/paper/2103.16076/) (2021)
- [Self-Supervised Video Forensics by Audio-Visual Anomaly Detection](https://mlsanity.com/paper/2301.01767/) (2023)
- [Learning JPEG Compression Artifacts for Image Manipulation Detection and Localization](https://mlsanity.com/paper/2108.12947/) (2021)
- [ObjectFormer for Image Manipulation Detection and Localization](https://mlsanity.com/paper/2203.14681/) (2022)
- [Open-Domain, Content-based, Multi-modal Fact-checking of Out-of-Context Images via Online Resources](https://mlsanity.com/paper/2112.00061/) (2021)
- [Making Images Real Again: A Comprehensive Survey on Deep Image Composition](https://mlsanity.com/paper/2106.14490/) (2021)
- [Predicting Video with VQVAE](https://mlsanity.com/paper/2103.01950/) (2021)
- [Shadows Don't Lie and Lines Can't Bend! Generative Models don't know Projective Geometry...for now](https://mlsanity.com/paper/2311.17138/) (2023)
- [BiHPF: Bilateral High-Pass Filters for Robust Deepfake Detection](https://mlsanity.com/paper/2109.00911/) (2021)
- [Online Detection of AI-Generated Images](https://mlsanity.com/paper/2310.15150/) (2023)
- [Multimodal Automated Fact-Checking: A Survey](https://mlsanity.com/paper/2305.13507/) (2023)
- [Community Forensics: Using Thousands of Generators to Train Fake Image Detectors](https://mlsanity.com/paper/2411.04125/) (2024)
- [Deepfake Network Architecture Attribution](https://mlsanity.com/paper/2202.13843/) (2022)
- [FReTAL: Generalizing Deepfake Detection using Knowledge Distillation and Representation Learning](https://mlsanity.com/paper/2105.13617/) (2021)
- [IML-ViT: Benchmarking Image Manipulation Localization by Vision Transformer](https://mlsanity.com/paper/2307.14863/) (2023)
- [IMDL-BenCo: A Comprehensive Benchmark and Codebase for Image Manipulation Detection & Localization](https://mlsanity.com/paper/2406.10580/) (2024)
- [Diffusion Facial Forgery Detection](https://mlsanity.com/paper/2401.15859/) (2024)
- [Language-Driven Image Style Transfer](https://mlsanity.com/paper/2106.00178/) (2021)
- [CoReD: Generalizing Fake Media Detection with Continual Representation using Distillation](https://mlsanity.com/paper/2107.02408/) (2021)
- [One Detector to Rule Them All: Towards a General Deepfake Attack Detection Framework](https://mlsanity.com/paper/2105.00187/) (2021)
- [Pixel-Inconsistency Modeling for Image Manipulation Localization](https://mlsanity.com/paper/2310.00234/) (2023)
- [Self-Adversarial Training incorporating Forgery Attention for Image Forgery Localization](https://mlsanity.com/paper/2107.02434/) (2021)
- [Weakly-supervised deepfake localization in diffusion-generated images](https://mlsanity.com/paper/2311.04584/) (2023)
- [Towards Generic Image Manipulation Detection with Weakly-Supervised Self-Consistency Learning](https://mlsanity.com/paper/2309.01246/) (2023)
- [Pre-training-free Image Manipulation Localization through Non-Mutually Exclusive Contrastive Learning](https://mlsanity.com/paper/2309.14900/) (2023)
- [Mixture of Low-rank Experts for Transferable AI-Generated Image Detection](https://mlsanity.com/paper/2404.04883/) (2024)

## 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.