一句话：提出 FIGCPS，用深度强化学习在无需被测系统知识和历史日志的情况下自动生成信息物理系统的故障诱发输入。
信息物理系统（CPS）由控制逻辑与物理过程交织而成，广泛用于医疗监控、自动驾驶和水处理等安全攸关场景，但难以获得能使其失效的测试用例。本文提出 FIGCPS：一种无需被测 CPS 知识或历史日志的故障诱发输入生成方法。它采用深度强化学习与被测系统交互，以奖励引导搜索，并自适应收集系统信息以缩短训练时间、探索不同状态。该工作首次面向同时具有连续动作空间和高维离散动作空间的 CPS 生成故障诱发输入。实验表明，FIGCPS 的成功率高于现有方法，并在一个经过充分测试的 CPS 中发现两个新攻击。
Cyber-Physical Systems (CPSs) are composed of computational control logic and physical processes, which intertwine with each other. CPSs are widely used in various domains of daily life, including those safety-critical systems and infrastructures, such as medical monitoring, autonomous vehicles, and water treatment systems. It is thus critical to effectively test them. However, it is not easy to obtain test cases which can fail the CPS. In this work, we propose a failure-inducing input generation approach FIGCPS, which requires no knowledge of the CPS under test or any history logs of the CPS which are usually hard to obtain. Our approach adopts deep reinforcement learning techniques to interact with the CPS under test and effectively searches for failure-inducing input guided by rewards. Our approach adaptively collects information from the CPS, which reduces the training time and is also able to explore different states. Moreover, our approach is the first attempt to generate failure-inducing input for CPSs with both continuous action space and high-dimensional discrete action space, which are common for some classes of CPSs. The evaluation results show that FIGCPS not only achieves a higher success rate than the state-of-the-art approaches but also finds two new attacks in a well-tested CPS.
DOI 原文 ·
@inproceedings{paperbot6638,
title = {FIGCPS: Effective Failure-inducing Input Generation for Cyber-Physical Systems with Deep Reinforcement Learning},
author = {Shaohua Zhang and Shuang Liu and Jun Sun and Yuqi Chen and Wenzhi Huang and Jinyi Liu and Jian Liu and Jianye Hao},
booktitle = {ASE},
year = {2021},
doi = {10.1109/ase51524.2021.9678832}
}