Training-Free In-Context Forensic Chain for Image Manipulation Detection and Localization
This addresses security threats from image tampering by providing an interpretable and effective solution without the need for expensive labeled data, representing a novel approach in the field.
The paper tackles the problem of image manipulation detection and localization without requiring costly pixel-level annotations by proposing a training-free framework called In-Context Forensic Chain (ICFC) that uses multi-modal large language models, achieving competitive or superior performance compared to supervised methods across multiple benchmarks.
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.