Differential Privacy in Cooperative Multiagent Planning
Differential Privacy in Cooperative Multiagent Planning
复制标题
DOI：
10.48550/arxiv.2301.08811
复制
发表时间：
2023-01
期刊：
影响因子：
--
通讯作者：
Bo Chen;C. Hawkins;Mustafa O. Karabag;Cyrus Neary;M. Hale;U. Topcu
中科院分区：
文献类型：
--
作者：
Bo Chen;C. Hawkins;Mustafa O. Karabag;Cyrus Neary;M. Hale;U. Topcu
隐私感知的多代理系统必须保护代理的敏感数据，同时确保代理完成他们的共同目标。为了实现这一目标，我们提出了一个框架，以私有化合作多智能体决策问题的代理间的通信。我们研究序列决策问题制定为合作马尔可夫博弈达到避免目标。我们应用差异化隐私机制来私有化代理所传达的符号状态轨迹，然后分析隐私强度和团队绩效之间的权衡。对于一个给定的隐私水平，这种权衡严重依赖于代理的状态动作过程之间的总相关性。我们合成的政策，是强大的隐私减少的总相关值。数值实验表明，在这些政策下，团队的表现下降了3%，当比较私人与非私人的通信实现。相比之下，当使用忽略总体相关性而只优化团队绩效的基线策略时，团队的绩效下降了大约86%。
Privacy-aware multiagent systems must protect agents' sensitive data while simultaneously ensuring that agents accomplish their shared objectives. Towards this goal, we propose a framework to privatize inter-agent communications in cooperative multiagent decision-making problems. We study sequential decision-making problems formulated as cooperative Markov games with reach-avoid objectives. We apply a differential privacy mechanism to privatize agents' communicated symbolic state trajectories, and then we analyze tradeoffs between the strength of privacy and the team's performance. For a given level of privacy, this tradeoff is shown to depend critically upon the total correlation among agents' state-action processes. We synthesize policies that are robust to privacy by reducing the value of the total correlation. Numerical experiments demonstrate that the team's performance under these policies decreases by only 3 percent when comparing private versus non-private implementations of communication. By contrast, the team's performance decreases by roughly 86 percent when using baseline policies that ignore total correlation and only optimize team performance.