Weiheng Zhu, Gang Cao, Jing Liu et al. · Communication University of China · State Key Laboratory of Media Convergence and Communication +3 more
Dual-domain adversarial attack using spatial and frequency feature importance to evade AI-generated image detectors with strong cross-model transferability
Recent AI-generated image (AIGI) detectors achieve impressive accuracy under clean condition. In view of antiforensics, it is significant to develop advanced adversarial attacks for evaluating the security of such detectors, which remains unexplored sufficiently. This letter proposes a Dual-domain Feature Importance Attack (DuFIA) scheme to invalidate AIGI detectors to some extent. Forensically important features are captured by the spatially interpolated gradient and frequency-aware perturbation. The adversarial transferability is enhanced by jointly modeling spatial and frequency-domain feature importances, which are fused to guide the optimization-based adversarial example generation. Extensive experiments across various AIGI detectors verify the cross-model transferability, transparency and robustness of DuFIA.
cnntransformerCommunication University of China · State Key Laboratory of Media Convergence and Communication · Hunan University of Information Technology +2 more
ML Security Papers