Skip to content
Preprint

Evidence-Grounded Forensic Reasoning for Detecting and Grounding Multi-Modal Media Manipulation

Aug 2026 · 1 citation · ⚡ 1 influential · 53 references
Computer Science

TL;DR

Experiments show that EFR achieves state-of-the-art performance while producing structured forensic reasoning records that explicitly bind explanations to evidence, and mitigats credit misassignment across prediction tasks.

Abstract

Fake news increasingly relies on cross-modal image-text forgeries, making transparent and verifiable reasoning chains an urgent need for Detecting and Grounding Multi-Modal Media Manipulation (DGM4). Existing methods produce black-box detection results without any decision rationale, limiting their reliability in forensic practice. Multi-modal Large Language Models (MLLMs) offer a natural path toward explainability, but applying them to DGM4 raises two difficulties. First, models tend to generate explanations disconnected from predicted evidence locations, producing unverified attribution. Second, enforcing evidence-conclusion consistency requires active optimization, yet uniform training signals fail to distinguish localization tokens from classification tokens, making multi-head joint training unreliable. We propose a multi-modal manipulation detector based on an Evidence-Grounded Forensic Reasoning (EFR) framework. EFR introduces an Anchor-and-Verify reasoning chain that enforces modality-isolated perception before cross-modal comparison, with conclusion coordinates as explicit anchors to which downstream evidence must spatially correspond. A verifiable reward system then enforces evidence-conclusion consistency during training, while a Modality-Decoupled Advantage (MDA) routing mechanism mitigats credit misassignment across prediction tasks. Experiments show that EFR achieves state-of-the-art performance while producing structured forensic reasoning records that explicitly bind explanations to evidence.

View source

Similar papers

Conference Open access Aug 2026

Cross-Modal Inconsistency Mining for Detecting and Grounding Multi-Modal Media Manipulation

Cross-Modal Inconsistency Mining (CMIM), a lightweight framework that extracts image forgery cues through a noise residual forensic stream, mines image text inconsistency as the residual left after text tokens attend to image patches, and reuses these signals to detect and ground manipulations jointly is proposed.

Hai-Jia Zhong, Jia Ye, Silalai Phadboke et al. · 0 citations
Book Open access Sep 2026

Evidence-Guided Detection, Localization and Explanation for Text-Centric Image Forensics

An evidence-guided detector-localizer-reasoner system, where an image-level detector provides a global authenticity prior, a dedicated localizer extracts tampered regions as spatial grounding evidence, and an MLLM-based reasoner generates structured forensic reports grounded in this expert forensic evidence is proposed...

Pei-Feng Liu, Bin Li, Qing-Song Zhang et al. · 0 citations
Book Open access Sep 2026

Agentic Tool-Augmented Reasoning for Explainable Image Forgery Detection

Inspired by the forensic workflow of human judicial experts, Agentic Tool-Augmented Reasoning (ATAR) is proposed, a framework integrating 22 specialized forensic tools across seven complementary domains to autonomously detect, localize, and explain image forgeries through multi-turn reasoning.

Zhi-Ya Tan, Jing Huang, Chang-Tao Miao et al. · 0 citations
Review Aug 2026

Self-Reflective Multi-modal Reasoning for Short-Video Fake News Detection

SRM-FND is proposed, a self-reflective multimodal reasoning framework for short-video fake news detection that outperforms strong baselines, produces more reliable and interpretable predictions, and delivers noticeable improvements in cross-dataset performance.

Pin-Jie Xu, Yu-Zhou Yang, Zhi-Sheng Tan et al. · 0 citations
Preprint Sep 2026

From Sharp Eyes to Expert Mind: Internalizing Expert Knowledge in MLLMs for Tampered Text Detection

Tampered Text Detection (TTD) is essential for safeguarding document authenticity in security-critical workflows. Existing expert models are effective at capturing subtle manipulation traces but often generalize poorly across diverse document domains, while Multimodal Large Language Models (MLLMs) offer stronger semant...

Kai-Qing Lin, Song-Ze Li, Shen Chen et al. · 0 citations
Sep 2026

IN3SIGHT: Toward Cognitive Forensic Reasoning for OOC Misinformation Detection

Out-of-context (OOC) misinformation, where genuine images are paired with misleading text, poses substantial societal risks due to its deceptive narratives. Prior efforts primarily assess image–text consistency but often lack explainable judgments, limiting their usefulness for forensic validation. Recently, Multimodal...

Kai-Ge Li, Zhao-Qi Wu, Chao Huang et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.