A Decentralized Shotgun Approach for Team Deception
Caleb Probine, Mustafa O. Karabag, Ufuk Topcu

TL;DR
This paper introduces a scalable decentralized method for team deception in multi-agent systems, enabling agents to mask their true intentions from a supervisor while ensuring task completion.
Contribution
It proposes a novel decentralized deceptive policy synthesis algorithm that minimizes divergence from reference behaviors and handles supervisor-based agent elimination scenarios.
Findings
Algorithm scales linearly with number of agents
Ensures at least one agent achieves the task with high probability
Demonstrated effectiveness in package delivery scenario
Abstract
Deception is helpful for agents masking their intentions from an observer. We consider a team of agents deceiving their supervisor. The supervisor defines nominal behavior for the agents via reference policies, but the agents share an alternate task that they can only achieve by deviating from these references. As such, the agents use deceptive policies to complete the task while ensuring that their behaviors remain plausible to the supervisor. We propose a setting with centralized deceptive policy synthesis and decentralized execution. We model each agent with a Markov decision process and constrain the agents' deceptive policies so that, with high probability, at least one agent achieves the task. We then provide an algorithm to synthesize deceptive policies that ensure the deviations of all agents are small by minimizing the worst Kullback-Leibler divergence between any agent's…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsInformation and Cyber Security · Intelligence, Security, War Strategy · Advanced Malware Detection Techniques
