arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.04635cs.LGcs.SYeess.SY
收藏

基于强化学习的信息物理系统自动附着仿真

Automated Adversary Emulation for Cyber-Physical Systems via Reinforcement Learning

Pacific Northwest National Laboratory（太平洋西北国家实验室）；Michigan State University（密歇根州立大学）

Arnab Bhattacharya, Thiagarajan Ramachandran, Sandeep Banik, Chase P. Dowling, Shaunak D. Bopardikar

备注：
To appear in the Proceedings of the 18th IEEE International Conference on Intelligence and Security Informatics (2020)
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

摘要：

Advertisement仿真是一种攻击性练习，它提供了对系统抵御网络攻击的能力的全面评估。然而，对手模拟通常是一个手动过程，这使得其成本高昂，难以在具有复杂动态，漏洞和操作不确定性的网络物理系统（CPS）中部署。在本文中，我们开发了一个自动化的，域感知的方法来模拟CPS的对手。我们制定了一个马尔可夫决策过程（MDP）模型，以确定一个最佳的攻击序列的混合攻击图与网络（离散）和物理（连续）组件和相关的物理动力学。我们应用基于模型和无模型强化学习（RL）的方法来解决离散连续MDP在一个易于处理的方式。作为基准，我们还开发了一个贪婪攻击算法，并将其与RL程序进行比较。我们总结了我们的研究结果，通过数值研究传感器欺骗攻击在建筑物中比较所提出的算法的性能和解决方案的质量。

英文摘要：

Adversary emulation is an offensive exercise that provides a comprehensive assessment of a system's resilience against cyber attacks. However, adversary emulation is typically a manual process, making it costly and hard to deploy in cyber-physical systems (CPS) with complex dynamics, vulnerabilities, and operational uncertainties. In this paper, we develop an automated, domain-aware approach to adversary emulation for CPS. We formulate a Markov Decision Process (MDP) model to determine an optimal attack sequence over a hybrid attack graph with cyber (discrete) and physical (continuous) components and related physical dynamics. We apply model-based and model-free reinforcement learning (RL) methods to solve the discrete-continuous MDP in a tractable fashion. As a baseline, we also develop a greedy attack algorithm and compare it with the RL procedures. We summarize our findings through a numerical study on sensor deception attacks in buildings to compare the performance and solution quality of the proposed algorithms.

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。

↑