7 papers
Incentive Design for Multi-Agent Systems: A Bilevel Optimization Framework for Coordinating Independent Agents and Convergence Analysis
Xinyi Wei, Shuo Han, Jie Fu
Incentive design aims to guide the performance of a system towards a human's intention or preference. We study this problem in a multi-agent system with one leader and multiple fol…
Policy Gradient Methods for Information-Theoretic Opacity in Markov Decision Processes
Chongyang Shi, Sumukha Udupa, Michael R. Dorothy +2
Opacity, or non-interference, is a property ensuring that an external observer cannot infer confidential information (the "secret") from system observations. We introduce an inform…
Planning Stealthy Backdoor Attacks in MDPs with Observation-Based Triggers
Xinyi Wei, Shuo Han, Ahmed H. Hemida +2
This paper investigates backdoor attack planning in stochastic control systems modeled as Markov Decision Processes (MDPs). A backdoor attack involves an adversary deploying a poli…
Active Inference via Incentive Design: Eliciting Divergent Behaviors under Partial Observability
Xinyi Wei, Chongyang Shi, Shuo Han +3
We introduce Active Inference through Incentive Design, a framework in which a leader offers strategic incentive to elicit diverging behaviors from followers of different types, th…
Active Perception with Initial-State Uncertainty: A Policy Gradient Method
Chongyang Shi, Shuo Han, Michael Dorothy +1
This paper studies the synthesis of an active perception policy that maximizes the information leakage of the initial state in a stochastic system modeled as a hidden Markov model…
Robust Reward Design for Markov Decision Processes
Shuo Wu, Haoxiang Ma, Jie Fu +1
The problem of reward design examines the interaction between a leader and a follower, where the leader aims to shape the follower's behavior to maximize the leader's payoff by mod…
Covert Planning against Imperfect Observers
Haoxiang Ma, Chongyang Shi, Shuo Han +2
Covert planning refers to a class of constrained planning problems where an agent aims to accomplish a task with minimal information leaked to a passive observer to avoid detection…