arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2405.20641cs.CR
收藏

查询溯源分析:针对基于查询的黑盒攻击的高效鲁棒防御

Query Provenance Analysis: Efficient and Robust Defense against Query-based Black-box Attacks

Shaofei Li, Ziqi Zhang, Haomin Jia, Ding Li, Yao Guo, Xiangqun Chen

AI总结:

针对基于查询的黑盒攻击,提出查询溯源分析(QPA)方法,通过封装查询间历史关系作为序列特征并设计动态管理算法,有效抵御自适应攻击,显著降低攻击成功率并大幅提升吞吐量。

摘要:

基于查询的黑盒攻击已成为机器学习系统的重大威胁,攻击者可以操纵输入查询生成对抗样本,从而导致模型误分类。为了应对这些攻击,研究人员提出了状态防御模型(SDMs)来检测对抗性查询序列并拒绝与历史查询“相似”的查询。现有的最先进(SOTA)SDMs(例如BlackLight和PIHA)在防御这些攻击方面表现出极大的有效性。然而,最近的研究表明,它们容易受到Oracle引导的自适应拒绝采样(OARS)攻击,这是一种更强的自适应攻击策略。它可以很容易地与现有的攻击算法集成,利用从SDMs泄露的决策信息,通过生成具有微调扰动方向和步长的查询来逃避SDMs。在本文中,我们提出了一种新方法——查询溯源分析(QPA),用于构建更鲁棒和高效的SDMs。QPA将查询之间的历史关系封装为序列特征,以捕获良性查询序列和对抗性查询序列之间的根本差异。为了利用查询溯源,我们提出了一种具有动态管理的高效查询溯源分析算法。我们在四个广泛使用的数据集上使用六种基于查询的黑盒攻击算法,将QPA与两个基线BlackLight和PIHA进行了比较评估。结果表明,QPA在非自适应和自适应攻击的防御有效性和效率方面均优于基线。具体而言,QPA将OARS的攻击成功率(ASR)降低至4.08%,而BlackLight和PIHA分别为77.63%和87.72%。此外,QPA还实现了比BlackLight和PIHA分别高7.67倍和2.25倍的吞吐量。

英文摘要:

Query-based black-box attacks have emerged as a significant threat to machine learning systems, where adversaries can manipulate the input queries to generate adversarial examples that can cause misclassification of the model. To counter these attacks, researchers have proposed Stateful Defense Models (SDMs) for detecting adversarial query sequences and rejecting queries that are "similar" to the history queries. Existing state-of-the-art (SOTA) SDMs (e.g., BlackLight and PIHA) have shown great effectiveness in defending against these attacks. However, recent studies have shown that they are vulnerable to Oracle-guided Adaptive Rejection Sampling (OARS) attacks, which is a stronger adaptive attack strategy. It can be easily integrated with existing attack algorithms to evade the SDMs by generating queries with fine-tuned direction and step size of perturbations utilizing the leaked decision information from the SDMs. In this paper, we propose a novel approach, Query Provenance Analysis (QPA), for more robust and efficient SDMs. QPA encapsulates the historical relationships among queries as the sequence feature to capture the fundamental difference between benign and adversarial query sequences. To utilize the query provenance, we propose an efficient query provenance analysis algorithm with dynamic management. We evaluate QPA compared with two baselines, BlackLight and PIHA, on four widely used datasets with six query-based black-box attack algorithms. The results show that QPA outperforms the baselines in terms of defense effectiveness and efficiency on both non-adaptive and adaptive attacks. Specifically, QPA reduces the Attack Success Rate (ASR) of OARS to 4.08%, comparing to 77.63% and 87.72% for BlackLight and PIHA, respectively. Moreover, QPA also achieves 7.67x and 2.25x higher throughput than BlackLight and PIHA.

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。

↑