Search papers, labs, and topics across Lattice.
This paper addresses the security vulnerabilities of federated reinforcement learning (FRL) systems in autonomous vehicles, particularly focusing on the threat of poisoning attacks that can compromise decision-making. The authors introduce \alg, a novel framework that utilizes digital twins and historical model parameters to filter out malicious data and enhance the robustness of FRL systems in safety-critical scenarios. Theoretical convergence guarantees and empirical validation in realistic highway environments demonstrate that \alg effectively mitigates the impact of adversarial agents on the global control model.
Poisoning attacks can severely undermine autonomous vehicle systems, but a new framework effectively filters out malicious influences to ensure safer decision-making.
Federated reinforcement learning (FRL) is crucial for enabling collaborative learning across multiple agents without sharing raw data, thereby enhancing privacy and scalability in the decision-making process within dynamic vehicular environments. However, poisoning attacks pose a significant threat to the security and reliability of FRL-based systems, particularly in safety-critical autonomous driving, where this vulnerability remains largely unexplored. These attacks can compromise the global control model by subtly injecting malicious system parameters, leading to potential hazards. To counter these challenges, we present \alg (\underline{Sec}ure \underline{A}ggregation with \underline{p}oisoning-\underline{p}revention and historical reinforcement) as a defensive framework aimed at enhancing the robustness of FRL systems designed for safety-critical driving scenarios. \alg strategically integrates digital twins for rehearsal-based learning and leverages historical aggregated model parameters along with a selected central gradient to ensure that only benign data is aggregated, effectively mitigating the influence of malicious agents. Theoretical guarantees are provided for the convergence performance of \alg in the presence of poisoning attacks. We also validate the effectiveness of \alg using developed digital twins that model realistic highway environments to evaluate the control of autonomous vehicles under adversarial conditions.
