Saved in:
Bibliographic Details
Main Authors: Li, Haipeng, Peng, Rongxuan, Luo, Anwei, Tan, Shunquan, Chen, Changsheng, Antsiferova, Anastasia
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.06530
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915805414817792
author Li, Haipeng
Peng, Rongxuan
Luo, Anwei
Tan, Shunquan
Chen, Changsheng
Antsiferova, Anastasia
author_facet Li, Haipeng
Peng, Rongxuan
Luo, Anwei
Tan, Shunquan
Chen, Changsheng
Antsiferova, Anastasia
contents The rapid advancement of AI-Generated Content (AIGC) technologies poses significant challenges for authenticity assessment. However, existing evaluation protocols largely overlook anti-forensics attack, failing to ensure the comprehensive robustness of state-of-the-art AIGC detectors in real-world applications. To bridge this gap, we propose ForgeryEraser, a framework designed to execute universal anti-forensics attack without access to the target AIGC detectors. We reveal an adversarial vulnerability stemming from the systemic reliance on Vision-Language Models (VLMs) as shared backbones (e.g., CLIP), where downstream AIGC detectors inherit the feature space of these publicly accessible models. Instead of traditional logit-based optimization, we design a multi-modal guidance loss to drive forged image embeddings within the VLM feature space toward text-derived authentic anchors to erase forgery traces, while repelling them from forgery anchors. Extensive experiments demonstrate that ForgeryEraser causes substantial performance degradation to advanced AIGC detectors on both global synthesis and local editing benchmarks. Moreover, ForgeryEraser induces explainable forensic models to generate explanations consistent with authentic images for forged images. Our code will be made publicly available.
format Preprint
id arxiv_https___arxiv_org_abs_2602_06530
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Universal Anti-forensics Attack against Image Forgery Detection via Multi-modal Guidance
Li, Haipeng
Peng, Rongxuan
Luo, Anwei
Tan, Shunquan
Chen, Changsheng
Antsiferova, Anastasia
Computer Vision and Pattern Recognition
Cryptography and Security
The rapid advancement of AI-Generated Content (AIGC) technologies poses significant challenges for authenticity assessment. However, existing evaluation protocols largely overlook anti-forensics attack, failing to ensure the comprehensive robustness of state-of-the-art AIGC detectors in real-world applications. To bridge this gap, we propose ForgeryEraser, a framework designed to execute universal anti-forensics attack without access to the target AIGC detectors. We reveal an adversarial vulnerability stemming from the systemic reliance on Vision-Language Models (VLMs) as shared backbones (e.g., CLIP), where downstream AIGC detectors inherit the feature space of these publicly accessible models. Instead of traditional logit-based optimization, we design a multi-modal guidance loss to drive forged image embeddings within the VLM feature space toward text-derived authentic anchors to erase forgery traces, while repelling them from forgery anchors. Extensive experiments demonstrate that ForgeryEraser causes substantial performance degradation to advanced AIGC detectors on both global synthesis and local editing benchmarks. Moreover, ForgeryEraser induces explainable forensic models to generate explanations consistent with authentic images for forged images. Our code will be made publicly available.
title Universal Anti-forensics Attack against Image Forgery Detection via Multi-modal Guidance
topic Computer Vision and Pattern Recognition
Cryptography and Security
url https://arxiv.org/abs/2602.06530