Skip to content
Book Open access

GenText-Forensics: Challenge on Explainable Forensics and Adversarial Generation for Text-Centric Images

Nov 2026 · Proceedings of the 34th ACM International Conference on Multimedia · pp. 17457-17463 · 1 citation · 37 references

TL;DR

RealText-V2 is developed and the GenText-Forensics Challenge at ACM Multimedia 2026 is launched to advance reasoning-based text-centric image forensics, and analysis shows that leading systems consistently adopt modular expert pipelines, localization remains the primary performance driver, and evidence conditioning is central to reliable MLLM reasoning.

Abstract

AI-generated content has lowered the cost of forging text-centric images, threatening financial, legal, and information systems. Building on DocShield and its RealText-V1 benchmark, we develop RealText-V2 and launch the GenText-Forensics Challenge at ACM Multimedia 2026 to advance reasoning-based text-centric image forensics. The challenge formulates forgery analysis report generation as a unified task that integrates binary forgery detection, pixel-level tampering localization, and evidence-grounded explanation in a single structured report. RealText-V2 scales this formulation to broader languages, application domains, and manipulation types. Submissions are evaluated by detection F1, localization mF1, explanation BERTScore, and LLM-judged report quality. Our analysis shows that leading systems consistently adopt modular expert pipelines, localization remains the primary performance driver, and evidence conditioning is central to reliable MLLM reasoning. To foster open research on AI document safety, we publicly release RealText-V1, RealText-V2, and multi-scale DocShield model checkpoints through a unified collection.

Read PDF

Similar papers

Book Open access Sep 2026

Team MSU GenText-Forensics Challenge 2026 Technical Report

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.

Kirill Koltsov, Aleksandr Gushchin, D. Vatolin et al. · 0 citations
Sep 2026

ManiVid: Unified and Explainable Forensic Analysis of Manipulated Videos

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. · 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
Book Open access Nov 2026

Deepfake Forensics Workshop (DFF-2026): Detection, Attribution, Recognition, and Adversarial Challenges in the Era of AI-Generated Media

The rapid evolution of generative artificial intelligence is profoundly transforming the multimedia ecosystem, enabling the creation of highly realistic synthetic and manipulated content while simultaneously introducing unprecedented challenges for the authenticity, reliability, and trustworthiness of digital media. As...

Luca Guarnera, Francesco Guarnera, G. Puglisi et al. · 0 citations
Preprint Oct 2026

EviStress: Evidence Stress Learning for Generalizable Face Forgery Detection with Textual Explanations

The rapid spread of face forgeries on the Web challenges the credibility of visual content. In practical Web environments, manipulated media originate from evolving generation pipelines and undergo diverse processing during dissemination, making reliable authenticity assessment under unseen manipulations and visual cha...

Jiu-Yao Jing, Xuanyu Yi, Yu Zheng 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.