{"total":12,"rows":[{"id":"2107.00783","title":"Reinforcement Learning for Feedback-Enabled Cyber Resilience","created":"2021-07-02","cited_by_count":19,"area":null},{"id":"2301.00188","title":"New Challenges in Reinforcement Learning: A Survey of Security and Privacy","created":"2022-12-31","cited_by_count":7,"area":null},{"id":"2303.10838","title":"Deceptive Reinforcement Learning in Model-Free Domains","created":"2023-03-20","cited_by_count":7,"area":null},{"id":"2303.04257","title":"adaPARL: Adaptive Privacy-Aware Reinforcement Learning for Sequential-Decision Making Human-in-the-Loop Systems","created":"2023-03-07","cited_by_count":6,"area":null},{"id":"2305.10091","title":"Multi-Agent Reinforcement Learning: Methods, Applications, Visionary Prospects, and Challenges","created":"2023-05-17","cited_by_count":5,"area":null},{"id":"2308.08825","title":"Controlling Federated Learning for Covertness","created":"2023-08-17","cited_by_count":2,"area":null},{"id":"2310.16791","title":"Covert Planning against Imperfect Observers","created":"2023-10-25","cited_by_count":2,"area":null},{"id":"2303.00822","title":"Planning for Attacker Entrapment in Adversarial Settings","created":"2023-03-01","cited_by_count":1,"area":null},{"id":"2407.09809","title":"Preserving the Privacy of Reward Functions in MDPs through Deception","created":"2024-07-13","cited_by_count":1,"area":null},{"id":"2503.24284","title":"Value of Information-based Deceptive Path Planning Under Adversarial Interventions","created":"2025-03-31","cited_by_count":0,"area":null},{"id":"2602.24191","title":"Resilient Strategies for Stochastic Systems: How Much Does It Take to Break a Winning Strategy?","created":"2026-02-27","cited_by_count":0,"area":null},{"id":"2605.07174","title":"Repeated Deceptive Path Planning against Learnable Observer","created":"2026-05-08","cited_by_count":0,"area":null}],"next_cursor":null}