{"ID":2857049,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.10111","arxiv_id":"2510.10111","title":"Training-Free In-Context Forensic Chain for Image Manipulation Detection and Localization","abstract":"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.","short_abstract":"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 inter...","url_abs":"https://arxiv.org/abs/2510.10111","url_pdf":"https://arxiv.org/pdf/2510.10111v3","authors":"[\"Rui Chen\",\"Bin Liu\",\"Changtao Miao\",\"Xinghao Wang\",\"Yi Li\",\"Tao Gong\",\"Qi Chu\",\"Nenghai Yu\"]","published":"2025-10-11T08:42:31Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\",\"cs.CR\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}