Search papers, labs, and topics across Lattice.
This paper addresses the challenges posed by text-centric image manipulation by developing an evidence-guided detector-localizer-reasoner system for the GenText-Forensics Challenge at ACM Multimedia 2026. The system integrates an image-level authenticity detector, a localizer for identifying tampered regions, and a multi-layer language model (MLLM)-based reasoner that generates structured forensic reports based on the detected evidence. Achieving a score of 0.638 and ranking second in the challenge, the proposed method demonstrates significant advancements in authenticity detection and explanation in image forensics.
A novel evidence-guided system that not only detects image tampering but also spatially localizes and explains the manipulations, achieving state-of-the-art results in forensic analysis.
The rapid progress of AIGC has made text-centric image manipulation increasingly accessible, creating new forensic challenges that require not only authenticity detection but also spatial grounding and evidence-based explanation. This paper presents our solution to the GenText-Forensics Challenge at ACM Multimedia 2026. We propose 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. These modules are connected through a cascaded evidence flow: the detector gates the subsequent localization and prompting process, the localizer converts tamper responses into grounding boxes, and the reasoner is trained to synthesize the detector decision and localized evidence into the final report. As a key part of our method, we introduce iterative difficulty-aware mining to improve localization quality and apply report-mask consistency post-processing to align report grounding with predicted masks. On the official hidden test set, our system achieves a final score of 0.638 and ranks second in the challenge, validating the effectiveness of the proposed evidence-guided system. The code is available at https://github.com/peifengLiu42/ACMMM26-evidence-guided-detector-localizer-reasoner-system.
