BRNES: Enabling Security and Privacy-aware Experience Sharing in Multiagent Robotic and Autonomous Systems
This addresses critical security and privacy issues for decentralized multiagent systems, enabling safer and more efficient learning in real-world applications, though it builds incrementally on existing MARL and privacy techniques.
The paper tackles security and privacy vulnerabilities in experience sharing for multiagent reinforcement learning by proposing BRNES, which uses dynamic neighbor selection and weighted aggregation to mitigate Byzantine attacks and local differential privacy to protect against inference attacks. The framework achieves up to 8.32x faster performance than non-private baselines in adversarial settings.
Although experience sharing (ES) accelerates multiagent reinforcement learning (MARL) in an advisor-advisee framework, attempts to apply ES to decentralized multiagent systems have so far relied on trusted environments and overlooked the possibility of adversarial manipulation and inference. Nevertheless, in a real-world setting, some Byzantine attackers, disguised as advisors, may provide false advice to the advisee and catastrophically degrade the overall learning performance. Also, an inference attacker, disguised as an advisee, may conduct several queries to infer the advisors' private information and make the entire ES process questionable in terms of privacy leakage. To address and tackle these issues, we propose a novel MARL framework (BRNES) that heuristically selects a dynamic neighbor zone for each advisee at each learning step and adopts a weighted experience aggregation technique to reduce Byzantine attack impact. Furthermore, to keep the agent's private information safe from adversarial inference attacks, we leverage the local differential privacy (LDP)-induced noise during the ES process. Our experiments show that our framework outperforms the state-of-the-art in terms of the steps to goal, obtained reward, and time to goal metrics. Particularly, our evaluation shows that the proposed framework is 8.32x faster than the current non-private frameworks and 1.41x faster than the private frameworks in an adversarial setting.