{"total":86,"rows":[{"id":"2108.00401","title":"Advances in adversarial attacks and defenses in computer vision: A survey","created":"2021-08-01","cited_by_count":127,"area":null},{"id":"2205.01992","title":"Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoning","created":"2022-05-04","cited_by_count":94,"area":"safety"},{"id":"2106.05087","title":"Who Is the Strongest Enemy? Towards Optimal and Efficient Evasion Attacks in Deep RL","created":"2021-06-09","cited_by_count":55,"area":null},{"id":"2210.05927","title":"Efficient Adversarial Training without Attacking: Worst-Case-Aware Robust Reinforcement Learning","created":"2022-10-12","cited_by_count":43,"area":null},{"id":"2209.08025","title":"Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizability","created":"2022-09-16","cited_by_count":36,"area":null},{"id":"2311.09641","title":"RLHFPoison: Reward Poisoning Attack for Reinforcement Learning with Human Feedback in Large Language Models","created":"2023-11-16","cited_by_count":32,"area":"alignment"},{"id":"2310.14550","title":"Corruption-Robust Offline Reinforcement Learning with General Function Approximation","created":"2023-10-23","cited_by_count":31,"area":"offlinerl"},{"id":"2102.05800","title":"Robust Policy Gradient against Strong Data Corruption","created":"2021-02-11","cited_by_count":30,"area":null},{"id":"2312.12585","title":"BadRL: Sparse Targeted Backdoor Attack Against Reinforcement Learning","created":"2023-12-19","cited_by_count":30,"area":null},{"id":"2110.04471","title":"Provably Efficient Black-Box Action Poisoning Attacks Against Reinforcement Learning","created":"2021-10-09","cited_by_count":29,"area":null},{"id":"2510.23883","title":"Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges","created":"2025-10-27","cited_by_count":28,"area":"agents"},{"id":"2102.08492","title":"Reward Poisoning in Reinforcement Learning: Attacks Against Unknown Learners in Unknown Environments","created":"2021-02-16","cited_by_count":26,"area":null},{"id":"2203.08398","title":"COPA: Certifying Robust Policies for Offline Reinforcement Learning against Poisoning Attacks","created":"2022-03-16","cited_by_count":26,"area":"offlinerl"},{"id":"2102.05776","title":"Defense Against Reward Poisoning Attacks in Reinforcement Learning","created":"2021-02-10","cited_by_count":21,"area":null},{"id":"2208.13663","title":"Understanding the Limits of Poisoning Attacks in Episodic Reinforcement Learning","created":"2022-08-29","cited_by_count":21,"area":null},{"id":"2206.01888","title":"Reward Poisoning Attacks on Offline Multi-Agent Reinforcement Learning","created":"2022-06-04","cited_by_count":20,"area":"offlinerl"},{"id":"2107.00783","title":"Reinforcement Learning for Feedback-Enabled Cyber Resilience","created":"2021-07-02","cited_by_count":19,"area":null},{"id":"2107.01854","title":"Poisoning Attack against Estimating from Pairwise Comparisons","created":"2021-07-05","cited_by_count":14,"area":null},{"id":"2302.13851","title":"Implicit Poisoning Attacks in Two-Agent Reinforcement Learning: Adversarial Policies for Training-Time Attacks","created":"2023-02-27","cited_by_count":14,"area":null},{"id":"2206.00165","title":"Byzantine-Robust Online and Offline Distributed Reinforcement Learning","created":"2022-06-01","cited_by_count":13,"area":null},{"id":"2206.07813","title":"A Search-Based Testing Approach for Deep Reinforcement Learning Agents","created":"2022-06-15","cited_by_count":13,"area":null},{"id":"2201.02185","title":"Admissible Policy Teaching through Reward Design","created":"2022-01-06","cited_by_count":12,"area":null},{"id":"2309.17319","title":"Building Privacy-Preserving and Secure Geospatial Artificial Intelligence Foundation Models","created":"2023-09-29","cited_by_count":12,"area":null},{"id":"2312.00198","title":"Optimal Attack and Defense for Reinforcement Learning","created":"2023-11-30","cited_by_count":12,"area":null},{"id":"2505.23847","title":"Seven Security Challenges in Cross-domain Multi-agent LLM Systems","created":"2025-05-28","cited_by_count":12,"area":"agents"},{"id":"2110.09008","title":"When Are Linear Stochastic Bandits Attackable?","created":"2021-10-18","cited_by_count":10,"area":null},{"id":"2110.14432","title":"Iterative Teaching by Label Synthesis","created":"2021-10-27","cited_by_count":10,"area":null},{"id":"2307.07670","title":"Efficient Adversarial Attacks on Online Multi-agent Reinforcement Learning","created":"2023-07-15","cited_by_count":10,"area":null},{"id":"2205.14842","title":"Efficient Reward Poisoning Attacks on Online Deep Reinforcement Learning","created":"2022-05-30","cited_by_count":9,"area":null},{"id":"2110.11763","title":"Game Redesign in No-regret Game Playing","created":"2021-10-18","cited_by_count":8,"area":null},{"id":"2210.17467","title":"Iterative Teaching by Data Hallucination","created":"2022-10-31","cited_by_count":8,"area":null},{"id":"2402.12673","title":"Beyond Worst-case Attacks: Robust RL with Adaptive Defense via Non-dominated Policies","created":"2024-02-20","cited_by_count":8,"area":"deeprl"},{"id":"2502.08123","title":"Provably Robust Federated Reinforcement Learning","created":"2025-02-12","cited_by_count":8,"area":"deeprl"},{"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":"2402.03590","title":"Assessing the Impact of Distribution Shift on Reinforcement Learning Performance","created":"2024-02-05","cited_by_count":7,"area":"deeprl"},{"id":"2402.03741","title":"SUB-PLAY: Adversarial Policies against Partially Observed Multi-Agent Reinforcement Learning Systems","created":"2024-02-06","cited_by_count":7,"area":null},{"id":"2301.12595","title":"Adversarial Attacks on Adversarial Bandits","created":"2023-01-30","cited_by_count":6,"area":null},{"id":"2303.02725","title":"Local Environment Poisoning Attacks on Federated Reinforcement Learning","created":"2023-03-05","cited_by_count":6,"area":null},{"id":"2502.02844","title":"Wolfpack Adversarial Attack for Robust Multi-Agent Reinforcement Learning","created":"2025-02-05","cited_by_count":6,"area":null},{"id":"2208.00081","title":"Sampling Attacks on Meta Reinforcement Learning: A Minimax Formulation and Complexity Analysis","created":"2022-07-29","cited_by_count":5,"area":null},{"id":"2209.03540","title":"Reward Delay Attacks on Deep Reinforcement Learning","created":"2022-09-08","cited_by_count":5,"area":null},{"id":"2305.10681","title":"Black-Box Targeted Reward Poisoning Attack Against Online Deep Reinforcement Learning","created":"2023-05-18","cited_by_count":5,"area":null},{"id":"2402.09695","title":"Universal Black-Box Reward Poisoning Attack against Offline Reinforcement Learning","created":"2024-02-15","cited_by_count":4,"area":"offlinerl"},{"id":"2404.04714","title":"Data Poisoning Attacks on Off-Policy Policy Evaluation Methods","created":"2024-04-06","cited_by_count":4,"area":"safety"},{"id":"2112.00940","title":"Reward-Free Attacks in Multi-Agent Reinforcement Learning","created":"2021-12-02","cited_by_count":3,"area":null},{"id":"2112.05367","title":"Efficient Action Poisoning Attacks on Linear Contextual Bandits","created":"2021-12-10","cited_by_count":3,"area":null},{"id":"2311.00582","title":"Minimally Modifying a Markov Game to Achieve Any Nash Equilibrium and Value","created":"2023-11-01","cited_by_count":3,"area":null},{"id":"2405.16798","title":"Exploring Fairness in Educational Data Mining in the Context of the Right to be Forgotten","created":"2024-05-27","cited_by_count":3,"area":"safety"},{"id":"2212.06123","title":"Security of Deep Reinforcement Learning for Autonomous Driving: A Survey","created":"2022-12-12","cited_by_count":2,"area":"driving"},{"id":"2305.16621","title":"A Reminder of its Brittleness: Language Reward Shaping May Hinder Learning for Instruction Following Agents","created":"2023-05-26","cited_by_count":2,"area":null},{"id":"2307.07666","title":"Efficient Action Robust Reinforcement Learning with Probabilistic Policy Execution Uncertainty","created":"2023-07-15","cited_by_count":2,"area":null},{"id":"2310.05308","title":"Adversarial Attacks on Combinatorial Multi-Armed Bandits","created":"2023-10-08","cited_by_count":2,"area":null},{"id":"2402.13487","title":"Stealthy Adversarial Attacks on Stochastic Multi-Armed Bandits","created":"2024-02-21","cited_by_count":2,"area":null},{"id":"2403.04050","title":"Belief-Enriched Pessimistic Q-Learning against Adversarial State Perturbations","created":"2024-03-06","cited_by_count":2,"area":"deeprl"},{"id":"2403.08906","title":"Strategizing against Q-learners: A Control-theoretical Approach","created":"2024-03-13","cited_by_count":2,"area":"deeprl"},{"id":"2408.15200","title":"SpecGuard: Specification Aware Recovery for Robotic Autonomous Vehicles from Physical Attacks","created":"2024-08-27","cited_by_count":2,"area":"driving"},{"id":"2412.00797","title":"Online Poisoning Attack Against Reinforcement Learning under Black-box Environments","created":"2024-12-01","cited_by_count":2,"area":"deeprl"},{"id":"2604.01238","title":"Trustworthy AI-Driven Dynamic Hybrid RIS: Joint Optimization and Reward Poisoning-Resilient Control in Cognitive MISO Networks","created":"2026-03-27","cited_by_count":2,"area":"deeprl"},{"id":"2606.18697","title":"Stealthy World Model Manipulation via Data Poisoning","created":"2026-06-17","cited_by_count":2,"area":"wm"},{"id":"2111.14833","title":"Adversarial Attacks in Cooperative AI","created":"2021-11-29","cited_by_count":1,"area":null},{"id":"2203.05774","title":"Reinforcement Learning for Linear Quadratic Control is Vulnerable Under Cost Manipulation","created":"2022-03-11","cited_by_count":1,"area":"offlinerl"},{"id":"2204.11897","title":"Reinforcement Teaching","created":"2022-04-25","cited_by_count":1,"area":null},{"id":"2304.12151","title":"Policy Resilience to Environment Poisoning Attacks on Reinforcement Learning","created":"2023-04-24","cited_by_count":1,"area":null},{"id":"2306.08041","title":"Data Poisoning to Fake a Nash Equilibrium in Markov Games","created":"2023-06-13","cited_by_count":1,"area":"safety"},{"id":"2308.01274","title":"BRNES: Enabling Security and Privacy-aware Experience Sharing in Multiagent Robotic and Autonomous Systems","created":"2023-08-02","cited_by_count":1,"area":null},{"id":"2311.00859","title":"Optimal Cost Constrained Adversarial Attacks For Multiple Agent Systems","created":"2023-11-01","cited_by_count":1,"area":null},{"id":"2406.17425","title":"CuDA2: An approach for Incorporating Traitor Agents into Cooperative Multi-Agent Systems","created":"2024-06-25","cited_by_count":1,"area":null},{"id":"2411.13116","title":"Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning","created":"2024-11-20","cited_by_count":1,"area":"deeprl"},{"id":"2507.03372","title":"Action Robust Reinforcement Learning via Optimal Adversary Aware Policy Optimization","created":"2025-07-04","cited_by_count":1,"area":"deeprl"},{"id":"2605.02495","title":"Efficient Preference Poisoning Attack on Offline RLHF","created":"2026-05-04","cited_by_count":1,"area":"alignment"},{"id":"2312.12904","title":"PGN: A perturbation generation network against deep reinforcement learning","created":"2023-12-20","cited_by_count":0,"area":null},{"id":"2401.02652","title":"Adaptive Discounting of Training Time Attacks","created":"2024-01-05","cited_by_count":0,"area":"safety"},{"id":"2405.06689","title":"Policy Iteration for Two-Player General-Sum Stochastic Stackelberg Games","created":"2024-05-07","cited_by_count":0,"area":null},{"id":"2406.14217","title":"Defending Against Sophisticated Poisoning Attacks with RL-based Aggregation in Federated Learning","created":"2024-06-20","cited_by_count":0,"area":null},{"id":"2503.03676","title":"Optimally Installing Strict Equilibria","created":"2025-03-05","cited_by_count":0,"area":null},{"id":"2506.06891","title":"Robust In-Context Reinforcement Learning Under Reward Poisoning Attacks","created":"2025-06-07","cited_by_count":0,"area":"deeprl"},{"id":"2506.11172","title":"Collapsing Sequence-Level Data-Policy Coverage via Poisoning Attack in Offline Reinforcement Learning","created":"2025-06-12","cited_by_count":0,"area":"offlinerl"},{"id":"2507.18113","title":"Policy Disruption in Reinforcement Learning:Adversarial Attack with Large Language Models and Critical State Identification","created":"2025-07-24","cited_by_count":0,"area":null},{"id":"2508.09275","title":"Constrained Black-Box Attacks Against Cooperative Multi-Agent Reinforcement Learning","created":"2025-08-12","cited_by_count":0,"area":null},{"id":"2510.01479","title":"Density-Ratio Weighted Behavioral Cloning: Learning Control Policies from Corrupted Datasets","created":"2025-10-01","cited_by_count":0,"area":"offlinerl"},{"id":"2510.13792","title":"Provably Invincible Adversarial Attacks on Reinforcement Learning Systems: A Rate-Distortion Information-Theoretic Approach","created":"2025-10-15","cited_by_count":0,"area":"deeprl"},{"id":"2511.07701","title":"Diffusion Guided Adversarial State Perturbations in Reinforcement Learning","created":"2025-11-10","cited_by_count":0,"area":"deeprl"},{"id":"2512.08485","title":"Optimal Perturbation Budget Allocation for Data Poisoning in Offline Reinforcement Learning","created":"2025-12-09","cited_by_count":0,"area":"offlinerl"},{"id":"2604.10062","title":"When Can You Poison Rewards? A Tight Characterization of Reward Poisoning in Linear MDPs","created":"2026-04-11","cited_by_count":0,"area":"deeprl"},{"id":"2605.16312","title":"When Actions Disappear: Adversarial Action Removal in Self-Play Reinforcement Learning","created":"2026-05-04","cited_by_count":0,"area":"deeprl"},{"id":"2609.07051","title":"TrojanWorld: Backdooring World-Model Agents via Imagination Steering","created":"2026-09-07","cited_by_count":0,"area":"wm"}],"next_cursor":null}