# Training-Free In-Context Forensic Chain for Image Manipulation Detection and Localization

arXiv: https://arxiv.org/abs/2510.10111 · HTML: https://mlsanity.com/paper/2510.10111/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 30 references that are in the map.
- First posted on arXiv 11 Oct 2025.

## Builds on (most cited first, 16 of 16)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://mlsanity.com/paper/2202.12837/) (2022)
- [Large Language Models as Optimizers](https://mlsanity.com/paper/2309.03409/) (2023)
- [Generative Multimodal Models are In-Context Learners](https://mlsanity.com/paper/2312.13286/) (2023)
- [Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers](https://mlsanity.com/paper/2506.23918/) (2025)
- [Noiseprint: a CNN-based camera model fingerprint](https://mlsanity.com/paper/1808.08396/) (2018)
- [FakeShield: Explainable Image Forgery Detection and Localization via Multi-modal Large Language Models](https://mlsanity.com/paper/2410.02761/) (2024)
- [SIDA: Social Media Image Deepfake Detection, Localization and Explanation with Large Multimodal Model](https://mlsanity.com/paper/2412.04292/) (2024)
- [DyFo: A Training-Free Dynamic Focus Visual Search for Enhancing LMMs in Fine-Grained Visual Understanding](https://mlsanity.com/paper/2504.14920/) (2025)
- [Towards Generic Image Manipulation Detection with Weakly-Supervised Self-Consistency Learning](https://mlsanity.com/paper/2309.01246/) (2023)
- [Learning to Immunize Images for Tamper Localization and Self-Recovery](https://mlsanity.com/paper/2210.15902/) (2022)
- [A New Benchmark and Model for Challenging Image Manipulation Detection](https://mlsanity.com/paper/2311.14218/) (2023)
- [Context-Aware Weakly Supervised Image Manipulation Localization with SAM Refinement](https://mlsanity.com/paper/2503.20294/) (2025)

## Built on by (most cited first, 1 of 1)

- [Bridging the Modality Gap in Forensic Image Retrieval](https://mlsanity.com/paper/2606.12294/) (2026)

## Abstract (arXiv)

Advances in image tampering pose serious security threats, underscoring the need for effective image manipulation localization (IML). While supervised IML achieves strong performance, it depends on costly pixel-level annotations. Existing weakly supervised or training-free alternatives often underperform and lack interpretability. We propose the In-Context Forensic Chain (ICFC), a training-free framework that leverages multi-modal large language models (MLLMs) for interpretable IML tasks. ICFC integrates an objectified rule construction with adaptive filtering to build a reliable knowledge base and a multi-step progressive reasoning pipeline that mirrors expert forensic workflows from coarse proposals to fine-grained forensics results. This design enables systematic exploitation of MLLM reasoning for image-level classification, pixel-level localization, and text-level interpretability. Across multiple benchmarks, ICFC not only surpasses state-of-the-art training-free methods but also achieves competitive or superior performance compared to weakly and fully supervised approaches.