English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In this work, we study policy poisoning through state manipulation, alsoknown as sensor spoofing, and focus specifically on the case of an agentforming a control policy through batch learning in a linear-quadratic (LQ)system. In this scenario, an attacker aims to trick the learner intoimplementing a targeted malicious policy by manipulating the batch data beforethe agent begins its learning process. An attack model is crafted to carry outthe poisoning strategically, with the goal of modifying the batch data aslittle as possible to avoid detection by the learner. We establish anoptimization framework to guide the design of such policy poisoning attacks.The presence of bi-linear constraints in the optimization problem requires thedesign of a computationally efficient algorithm to obtain a solution.Therefore, we develop an iterative scheme based on the Alternating DirectionMethod of Multipliers (ADMM) which is able to return solutions that areapproximately optimal. Several case studies are used to demonstrate theeffectiveness of the algorithm in carrying out the sensor-based attack on thebatch-learning agent in LQ control systems.

Policy Poisoning in Batch Learning for Linear Quadratic Control Systems via State Manipulation