arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.05631cs.CRcs.LG
收藏

ConAML:面向信息物理系统的约束对抗机器学习

ConAML: Constrained Adversarial Machine Learning for Cyber-Physical Systems

University of Tennessee, Knoxville(田纳西大学诺克斯维尔分校);University of Illinois Springfield(伊利诺伊大学斯普林菲尔德分校)

Jiangnan Li, Yingyuan Yang, Jinyuan Stella Sun, Kevin Tomsovic, Hairong Qi

摘要:

最近的研究表明,表面上训练有素的机器学习(ML)模型非常容易受到对抗性示例的影响。随着ML技术在研究文献中成为网络物理系统(CPS)应用的流行解决方案,这些应用的安全性受到关注。然而,目前对对抗性机器学习(AML)的研究主要集中在纯网络空间领域。对抗性示例可能给CPS应用程序带来的风险尚未得到很好的研究。特别是,由于数据源的分布式特性和CPS所施加的固有物理约束,在以前的网络空间研究中广泛使用的威胁模型和最先进的AML算法变得不可行。我们通过提出约束对抗性机器学习(ConAML)来研究应用于CPS的ML的潜在漏洞,ConAML生成满足物理系统内在约束的对抗性示例。我们首先总结了CPS中的AML和现有网络空间系统中的AML之间的差异,并提出了ConAML的一般威胁模型。然后,我们设计了一个尽力而为的搜索算法,迭代生成具有线性物理约束的对抗性示例。我们评估我们的算法与两个典型的CPS,电网和水处理系统的模拟。结果表明,我们的ConAML算法可以有效地生成对抗性的例子,显着降低ML模型的性能,即使在实际的约束。

英文摘要:

Recent research demonstrated that the superficially well-trained machine learning (ML) models are highly vulnerable to adversarial examples. As ML techniques are becoming a popular solution for cyber-physical systems (CPSs) applications in research literatures, the security of these applications is of concern. However, current studies on adversarial machine learning (AML) mainly focus on pure cyberspace domains. The risks the adversarial examples can bring to the CPS applications have not been well investigated. In particular, due to the distributed property of data sources and the inherent physical constraints imposed by CPSs, the widely-used threat models and the state-of-the-art AML algorithms in previous cyberspace research become infeasible. We study the potential vulnerabilities of ML applied in CPSs by proposing Constrained Adversarial Machine Learning (ConAML), which generates adversarial examples that satisfy the intrinsic constraints of the physical systems. We first summarize the difference between AML in CPSs and AML in existing cyberspace systems and propose a general threat model for ConAML. We then design a best-effort search algorithm to iteratively generate adversarial examples with linear physical constraints. We evaluate our algorithms with simulations of two typical CPSs, the power grids and the water treatment system. The results show that our ConAML algorithms can effectively generate adversarial examples which significantly decrease the performance of the ML models even under practical constraints.

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。

↑