针对数据驱动控制方法的中毒攻击
Poisoning Attacks against Data-Driven Control Methods
摘要：
本文研究了针对数据驱动控制方法的中毒攻击。这项工作的动机是最近的趋势表明，在监督学习中，以恶意的方式稍微修改数据会大大降低训练模型的预测能力。我们将这些分析扩展到数据驱动控制方法的情况。具体来说，我们研究如何恶意的对手可以中毒的数据，以尽量减少使用这些数据训练的控制器的性能。我们表明，识别最具影响力的攻击归结为解决一个双层非凸优化问题，并提供理论见解的攻击。我们提出了一个通用的算法，找到这个问题的局部最优解，并说明我们的分析的情况下，基于模型参考的方法，虚拟参考反馈调整技术，并在数据驱动的方法的基础上Willems等人。引理。数值实验表明，数据集中最小但精心制作的更改足以显着降低数据驱动控制方法的性能，甚至使闭环系统不稳定。
英文摘要：
This paper investigates poisoning attacks against data-driven control methods. This work is motivated by recent trends showing that, in supervised learning, slightly modifying the data in a malicious manner can drastically deteriorate the prediction ability of the trained model. We extend these analyses to the case of data-driven control methods. Specifically, we investigate how a malicious adversary can poison the data so as to minimize the performance of a controller trained using this data. We show that identifying the most impactful attack boils down to solving a bi-level non-convex optimization problem, and provide theoretical insights on the attack. We present a generic algorithm finding a local optimum of this problem and illustrate our analysis in the case of a model-reference based approach, the Virtual Reference Feedback Tuning technique, and on data-driven methods based on Willems et al. lemma. Numerical experiments reveal that minimal but well-crafted changes in the dataset are sufficient to deteriorate the performance of data-driven control methods significantly, and even make the closed-loop system unstable.
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。
