Universal Anti-forensics Attack against Image Forgery Detection via Multi-modal Guidance
This addresses a critical security gap in real-world AIGC authenticity assessment by exposing and exploiting vulnerabilities in widely used vision-language models, though it is incremental in building on existing adversarial attack methods.
The paper tackles the vulnerability of AI-generated content (AIGC) detectors to anti-forensics attacks by proposing ForgeryEraser, a framework that uses multi-modal guidance to erase forgery traces in images, causing substantial performance degradation in advanced detectors and inducing explainable models to misclassify forged images as authentic.
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.