Generating Attribution Reports for Manipulated Facial Images: A Dataset and Baseline

Authors: Jingchun Lian, Lingyu Liu, Yaxiong Wang, Yujiao Wu, Lianwei Wu, Li Zhu, Zhedong Zheng

Published in ACL, 2026

Recommended citation: Jingchun Lian, Lingyu Liu, Yaxiong Wang, Yujiao Wu, Lianwei Wu, Li Zhu, Zhedong Zheng, "Generating Attribution Reports for Manipulated Facial Images: A Dataset and Baseline." ACL, 2026.
Download PDF: https://zdzheng.xyz/files/2026/ACL_Lian.pdf

Code is available at: https://github.com/NattyLianJc/Generating-Attribution-Reports

Abstract: Existing facial forgery detection methods typically focus on binary classification or pixel-level localization, providing little semantic insight into the nature of the manipulation. To address this, we introduce Forgery Attribution Report Generation, a new multimodal task that jointly localizes forged regions ("Where") and generates natural language explanations grounded in the editing process ("Why"). This dual-focus approach goes beyond traditional forensics, providing a comprehensive understanding of the manipulation. To enable research in this domain, we present Multi-Modal Tamper Tracing (MMTT), a large-scale dataset of 152,217 samples, each with a process-derived ground-truth mask and a human-authored textual description, ensuring high annotation precision and linguistic richness. We further propose ForgeryTalker, a unified end-to-end framework that integrates vision and language via a shared encoder (image encoder + Q-former) and dual decoders for mask and text generation, enabling coherent cross-modal reasoning. Experiments show that ForgeryTalker achieves competitive performance on both report generation and forgery localization subtasks, i.e., 59.3 CIDEr and 73.67 IoU, respectively, establishing a baseline for explainable multimedia forensics. Dataset and code will be released to foster future research.

@inproceedings{lian2026generating,
author = "Lian, Jingchun and Liu, Lingyu and Wang, Yaxiong and Wu, Yujiao and Wu, Lianwei and Zhu, Li and Zheng, Zhedong",
title = "Generating Attribution Reports for Manipulated Facial Images: A Dataset and Baseline",
abstract = {Existing facial forgery detection methods typically focus on binary classification or pixel-level localization, providing little semantic insight into the nature of the manipulation. To address this, we introduce Forgery Attribution Report Generation, a new multimodal task that jointly localizes forged regions ("Where") and generates natural language explanations grounded in the editing process ("Why"). This dual-focus approach goes beyond traditional forensics, providing a comprehensive understanding of the manipulation. To enable research in this domain, we present Multi-Modal Tamper Tracing (MMTT), a large-scale dataset of 152,217 samples, each with a process-derived ground-truth mask and a human-authored textual description, ensuring high annotation precision and linguistic richness. We further propose ForgeryTalker, a unified end-to-end framework that integrates vision and language via a shared encoder (image encoder + Q-former) and dual decoders for mask and text generation, enabling coherent cross-modal reasoning. Experiments show that ForgeryTalker achieves competitive performance on both report generation and forgery localization subtasks, i.e., 59.3 CIDEr and 73.67 IoU, respectively, establishing a baseline for explainable multimedia forensics. Dataset and code will be released to foster future research.},
booktitle = "ACL",
code = "https://github.com/NattyLianJc/Generating-Attribution-Reports",
url = "https://zdzheng.xyz/files/2026/ACL\_Lian.pdf",
funding = "2025A1515012281, SBZ20250900116, FDCT/0043/2025/RIA1",
year = "2026" }