Sep 2026· Proceedings of the 34th ACM International Conference on Multimedia· 0 citations· 15 references
Computer Science
TL;DR
A decomposed chain-of-thought (CoT) pipeline that combines a document tampering detector (DTD) with two Qwen3-VL-32B vision-language models, each LoRA-adapted to a distinct sub-task is presented.
Abstract
Document text forgery has evolved beyond simple pixel-level manipulation: modern attacks alter not only the appearance of a document but also its meaning, and increasingly target the OCR?LLM pipelines that consume such documents. The ACM MM 2026 GenText-Forensics challenge therefore requires systems that not only decide whether a multilingual text image is forged, but also localize the point of manipulation, identify the attack type, and produce a human-readable forensic report with supporting evidence. We present our solution, a decomposed chain-of-thought (CoT) pipeline that combines a document tampering detector (DTD) with two Qwen3-VL-32B vision--language models, each LoRA-adapted to a distinct sub-task. DTD produces tampering probability maps that are converted into numbered candidate regions; a first model (the Filterer ) validates these regions and assigns a preliminary forgery type, while a second model (the Semantic Detective ) merges and re-grounds the surviving regions, searches for purely semantic anomalies that are invisible to pixel-level detectors, and writes the final report. Both models are trained by distilling chain-of-thought traces from a privileged Qwen3-VL-235B teacher that has access to ground-truth masks and reports. Our approach secured third place in the ACM MM 2026 GenText-Forensics challenge. We describe the data preparation, test-time augmentation, region rendering, distillation protocol, and training configuration in detail, and report ablations over detector thresholds, prompt designs, and pipeline decompositions.
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.· Proceedings of the 34th ACM...· 0 citations
(k)-SwordStamp is designed: semantic watermarks with order-robust detection over sub-sentence units, reducing sensitivity to attacker-chosen structure at a small quality cost.
Abdulrahman Diaa, Jonathan Petit, Florian Kerschbaum· 2 citations
LeakageBench provides a diagnostic benchmark for high-recall, spatially grounded PII redaction in document images and shows that stronger detection and tool assistance improve localization without making most pages safe for release.
V. Kumar, Santhosh Venkatesh, Ivan P. Yamshchikov· 0 citations
Image-to-text jailbreaks place harmful intent in text, image content, or the relationship between them. We examine image-side factors across four published attack families on a 313-prompt StrongREJECT slice, using five multimodal models and an additional appendix evaluation of InternVL3.5-8B. The harmful instruction is...
Bo-Yuan Chen, Yehia Dawoud, Hailemariam Mersha et al.· 0 citations
We introduce Tokenization-Invariant Watermarking (TI-WM), a method that embeds a watermark during token generation but keys and scores it on canonicalized UTF-8 bytes. The detector does not invoke the tokenizer. Canonicalizer-preserving edits leave its score unchanged; other localized canonical-byte edits affect a boun...
This work introduces ManiVid, a unified forensic analysis task covering forgery detection, artifact grounding, and anomaly explanation for manipulated videos, and proposes ManiVidLens, a unified framework for explainable video forgery analysis.
Heng-Rui Kang, Zhong-Hao Yan, Yuxuan Yang et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.