5 papers
DifAttack++: Query-Efficient Black-Box Adversarial Attack via Hierarchical Disentangled Feature Space in Cross-Domain
Jun Liu, Jiantao Zhou, Jiandian Zeng +2
This work investigates efficient score-based black-box adversarial attacks that achieve a high Attack Success Rate (ASR) and good generalization ability. We propose a novel attack…
Deferred Poisoning: Making the Model More Vulnerable via Hessian Singularization
Yuhao He, Jinyu Tian, Xianwei Zheng +3
Recent studies have shown that deep learning models are very vulnerable to poisoning attacks. Many defense methods have been proposed to address this issue. However, traditional po…
Data-Free Universal Attack by Exploiting the Intrinsic Vulnerability of Deep Models
YangTian Yan, Jinyu Tian
Deep neural networks (DNNs) are susceptible to Universal Adversarial Perturbations (UAPs), which are instance agnostic perturbations that can deceive a target model across a wide r…
Anti-Diffusion: Preventing Abuse of Modifications of Diffusion-Based Models
Zheng Li, Liangbin Xie, Jiantao Zhou +3
Although diffusion-based techniques have shown remarkable success in image generation and editing tasks, their abuse can lead to severe negative social impacts. Recently, some work…
DAT: Improving Adversarial Robustness via Generative Amplitude Mix-up in Frequency Domain
Fengpeng Li, Kemou Li, Haiwei Wu +2
To protect deep neural networks (DNNs) from adversarial attacks, adversarial training (AT) is developed by incorporating adversarial examples (AEs) into model training. Recent stud…