arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2408.10673cs.CR
收藏

迭代窗口均值滤波:挫败基于扩散的对抗性纯化

Iterative Window Mean Filter: Thwarting Diffusion-based Adversarial Purification

Hanrui Wang, Ruoxi Sun, Cunjian Chen, Minhui Xue, Lay-Ki Soon, Shuo Wang, Zhe Jin

AI总结:

针对人脸认证系统易受对抗攻击、现有防御存在缺陷或牺牲准确率的问题,提出迭代窗口均值滤波器IWMF及融合扩散模型的IWMF-Diff纯化框架,作为预处理模块消弭扰动,在四项关键指标上超越现有最优方法DiffPure。

摘要:

人脸认证系统带来了极大便利与长足发展,但由于其对不易察觉的扰动(如对抗攻击)具有敏感性,现已变得不可靠。现有防御方法在面对各类攻击算法与自适应攻击时往往存在缺陷,或是为提升安全性而牺牲准确率。为应对这些挑战,我们开发了一种新颖且高效的非深度学习图像滤波器,名为迭代窗口均值滤波器(Iterative Window Mean Filter, IWMF),并提出了一种新的对抗性纯化框架IWMF-Diff,该框架整合了IWMF与去噪扩散模型。这些方法可作为预处理模块消除对抗扰动,无需对目标系统进行进一步修改或重新训练。我们证明所提方法满足四项关键要求:保留准确率、提升安全性、对不同场景下的各类威胁具有泛化性、对自适应攻击有更强的抵抗能力。其性能优于当前最先进的对抗性纯化方法DiffPure。

英文摘要:

Face authentication systems have brought significant convenience and advanced developments, yet they have become unreliable due to their sensitivity to inconspicuous perturbations, such as adversarial attacks. Existing defenses often exhibit weaknesses when facing various attack algorithms and adaptive attacks or compromise accuracy for enhanced security. To address these challenges, we have developed a novel and highly efficient non-deep-learning-based image filter called the Iterative Window Mean Filter (IWMF) and proposed a new framework for adversarial purification, named IWMF-Diff, which integrates IWMF and denoising diffusion models. These methods can function as pre-processing modules to eliminate adversarial perturbations without necessitating further modifications or retraining of the target system. We demonstrate that our proposed methodologies fulfill four critical requirements: preserved accuracy, improved security, generalizability to various threats in different settings, and better resistance to adaptive attacks. This performance surpasses that of the state-of-the-art adversarial purification method, DiffPure.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑