Trust helps protect secrets in networked agent systems while sharing information
Trust-Aware Adaptive Disclosure for Inference Privacy Preservation in Multi-Agent Networks
Multiagent SystemsCryptography and Security
Summary
Some systems use many agents that share information to work together, but these agents have secret goals they don’t want others to learn. The authors look at ways to keep these goals hidden while still sharing information to reach agreements. They propose a method where agents share messages based on how much they trust each other, using a careful strategy to keep secrets safer. Their tests show this approach reduces how well outsiders can guess the secret goals, while still allowing the agents to work well together.
multi-agent systemsprivacy preservationtrust relationshipsconsensus algorithmsgoal inference attacksstochastic policyinformation disclosureadversarial inferencenetwork securityadaptive control
Authors
Puspanjali Ghoshal, Tobias J. Oechtering
Abstract
Agent based systems are increasingly deployed in information critical systems including healthcare management systems, and smart grids. In this paper, we consider a multi-agent system where each agent has a latent goal that needs to be kept hidden from observing adversaries. More specifically, this paper studies privacy-preserving consensus in networked multi-agent systems under goal inference attacks. We propose a Trust-Aware Privacy Control framework that adapts message disclosure based on the dynamic trust relationships between agents. The proposed method controls information release using a trust-dependent stochastic policy. This enables a tradeoff between consensus performance and privacy preservation. Experiments demonstrate that the proposed method reduces adversarial goal inference accuracy compared to representative baselines, while maintaining competitive consensus utility, thereby highlighting the effectiveness of trust-aware mechanisms in privacy preservation of the agents in multi-agent systems.