论文标题
离线数据中毒攻击对线性动力学系统的分析和可检测性
Analysis and Detectability of Offline Data Poisoning Attacks on Linear Dynamical Systems
论文作者
论文摘要
近年来，人们对数据中毒攻击对数据驱动控制方法的影响越来越感兴趣。中毒攻击是机器学习社区众所周知的，但是，它利用了诸如跨样本独立性之类的假设，通常不适合线性动力学系统。因此，这些系统需要与在I.I.D. \设置中为监督学习问题开发的攻击和检测方法不同的攻击和检测方法。由于大多数数据驱动的控制算法都利用了最小二乘估计器，因此我们研究中毒如何通过统计测试的镜头影响最小二乘估计，并质疑可以检测到数据中毒攻击的方式。我们在哪些条件下确定与数据兼容的模型集包括系统的真实模型，我们分析了攻击者的不同中毒策略。根据所提出的论点，我们提出了对最小二乘估算器的隐秘数据中毒攻击，该攻击可以逃脱经典的统计测试，并通过显示拟议攻击的效率来结束。
In recent years, there has been a growing interest in the effects of data poisoning attacks on data-driven control methods. Poisoning attacks are well-known to the Machine Learning community, which, however, make use of assumptions, such as cross-sample independence, that in general do not hold for linear dynamical systems. Consequently, these systems require different attack and detection methods than those developed for supervised learning problems in the i.i.d.\ setting. Since most data-driven control algorithms make use of the least-squares estimator, we study how poisoning impacts the least-squares estimate through the lens of statistical testing, and question in what way data poisoning attacks can be detected. We establish under which conditions the set of models compatible with the data includes the true model of the system, and we analyze different poisoning strategies for the attacker. On the basis of the arguments hereby presented, we propose a stealthy data poisoning attack on the least-squares estimator that can escape classical statistical tests, and conclude by showing the efficiency of the proposed attack.
