{"total":166,"rows":[{"id":"2210.10760","title":"Scaling Laws for Reward Model Overoptimization","created":"2022-10-19","cited_by_count":1095,"area":"alignment"},{"id":"2302.04578","title":"Adversarial Example Does Good: Preventing Painting Imitation from Diffusion Models via Adversarial Examples","created":"2023-02-09","cited_by_count":167,"area":"diffusion"},{"id":"2406.02900","title":"Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms","created":"2024-06-05","cited_by_count":143,"area":"alignment"},{"id":"2101.08452","title":"Robust Reinforcement Learning on State Observations with Learned Optimal Adversary","created":"2021-01-21","cited_by_count":135,"area":null},{"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":"2110.05038","title":"Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPs","created":"2021-10-11","cited_by_count":122,"area":null},{"id":"2109.14523","title":"Online Robust Reinforcement Learning with Model Uncertainty","created":"2021-09-29","cited_by_count":96,"area":null},{"id":"2205.07344","title":"Policy Gradient Method For Robust Reinforcement Learning","created":"2022-05-15","cited_by_count":69,"area":null},{"id":"2105.00579","title":"BACKDOORL: Backdoor Attack against Competitive Reinforcement Learning","created":"2021-05-02","cited_by_count":68,"area":null},{"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":"2202.10910","title":"Sound Adversarial Audio-Visual Navigation","created":"2022-02-22","cited_by_count":48,"area":null},{"id":"2209.08162","title":"Uncertainty Quantification of Collaborative Detection for Self-Driving","created":"2022-09-16","cited_by_count":46,"area":null},{"id":"2106.09292","title":"CROP: Certifying Robust Policies for Reinforcement Learning through Functional Smoothing","created":"2021-06-17","cited_by_count":42,"area":null},{"id":"2104.00671","title":"TRS: Transferability Reduced Ensemble via Encouraging Gradient Diversity and Model Smoothness","created":"2021-04-01","cited_by_count":38,"area":null},{"id":"2205.14691","title":"On the Robustness of Safe Reinforcement Learning under Observational Perturbations","created":"2022-05-29","cited_by_count":38,"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":"2307.16212","title":"Robust Multi-Agent Reinforcement Learning with State Uncertainty","created":"2023-07-30","cited_by_count":36,"area":null},{"id":"2104.01789","title":"Deep Learning-Based Autonomous Driving Systems: A Survey of Attacks and Defenses","created":"2021-04-05","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":"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":"2211.15557","title":"Beyond CAGE: Investigating Generalization of Learned Autonomous Network Defense Policies","created":"2022-11-28","cited_by_count":23,"area":null},{"id":"2410.23687","title":"Adversarial Attacks of Vision Tasks in the Past 10 Years: A Survey","created":"2024-10-31","cited_by_count":23,"area":"mllm"},{"id":"2212.02705","title":"What is the Solution for State-Adversarial Multi-Agent Reinforcement Learning?","created":"2022-12-06","cited_by_count":22,"area":null},{"id":"2301.00858","title":"Robust Average-Reward Markov Decision Processes","created":"2023-01-02","cited_by_count":22,"area":null},{"id":"2102.05776","title":"Defense Against Reward Poisoning Attacks in Reinforcement Learning","created":"2021-02-10","cited_by_count":21,"area":null},{"id":"2109.03540","title":"A Survey of Deep Reinforcement Learning in Recommender Systems: A Systematic Review and Future Directions","created":"2021-09-08","cited_by_count":21,"area":null},{"id":"2204.07932","title":"Towards Comprehensive Testing on the Robustness of Cooperative Multi-agent Reinforcement Learning","created":"2022-04-17","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":"2301.07487","title":"Adversarial Robust Deep Reinforcement Learning Requires Redefining Robustness","created":"2023-01-17","cited_by_count":19,"area":null},{"id":"2405.20539","title":"SleeperNets: Universal Backdoor Poisoning Attacks Against Reinforcement Learning Agents","created":"2024-05-30","cited_by_count":19,"area":"safety"},{"id":"2108.03803","title":"Mis-spoke or mis-lead: Achieving Robustness in Multi-Agent Communicative Reinforcement Learning","created":"2021-08-09","cited_by_count":18,"area":null},{"id":"2405.19424","title":"Diffusion Policy Attacker: Crafting Adversarial Attacks for Diffusion-based Policies","created":"2024-05-29","cited_by_count":18,"area":"diffusion"},{"id":"2302.03322","title":"Attacking Cooperative Multi-Agent Reinforcement Learning by Adversarial Minority Influence","created":"2023-02-07","cited_by_count":17,"area":null},{"id":"2308.10797","title":"Stabilizing Unsupervised Environment Design with a Learned Adversary","created":"2023-08-21","cited_by_count":17,"area":null},{"id":"2311.09994","title":"Towards more Practical Threat Models in Artificial Intelligence Security","created":"2023-11-16","cited_by_count":17,"area":null},{"id":"2304.00010","title":"Towards Reasonable Budget Allocation in Untargeted Graph Structure Attacks via Gradient Debias","created":"2023-03-29","cited_by_count":16,"area":null},{"id":"2412.10713","title":"RAT: Adversarial Attacks on Deep Reinforcement Agents for Targeted Behaviors","created":"2024-12-14","cited_by_count":16,"area":"deeprl"},{"id":"2106.15587","title":"Generalization of Reinforcement Learning with Policy-Aware Adversarial Data Augmentation","created":"2021-06-29","cited_by_count":15,"area":null},{"id":"2206.10057","title":"Robust Deep Reinforcement Learning through Bootstrapped Opportunistic Curriculum","created":"2022-06-21","cited_by_count":15,"area":null},{"id":"2209.06866","title":"Robust Constrained Reinforcement Learning","created":"2022-09-14","cited_by_count":15,"area":null},{"id":"2211.03769","title":"Are AlphaZero-like Agents Robust to Adversarial Perturbations?","created":"2022-11-07","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":"2103.06473","title":"Multi-Task Federated Reinforcement Learning with Adversaries","created":"2021-03-11","cited_by_count":13,"area":null},{"id":"2106.15860","title":"Understanding Adversarial Attacks on Observations in Deep Reinforcement Learning","created":"2021-06-30","cited_by_count":13,"area":null},{"id":"2109.07723","title":"Targeted Attack on Deep RL-based Autonomous Driving with Learned Visual Patterns","created":"2021-09-16","cited_by_count":13,"area":"driving"},{"id":"2206.05533","title":"Rare event failure test case generation in Learning-Enabled-Controllers","created":"2022-06-11","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":"2305.12751","title":"Testing of Deep Reinforcement Learning Agents with Surrogate Models","created":"2023-05-22","cited_by_count":13,"area":null},{"id":"2108.13872","title":"Reinforcement Learning Based Sparse Black-box Adversarial Attack on Video Recognition Models","created":"2021-08-29","cited_by_count":12,"area":null},{"id":"2112.09025","title":"Deep Reinforcement Learning Policies Learn Shared Adversarial Features Across MDPs","created":"2021-12-16","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":"2102.07244","title":"Resilient Machine Learning for Networked Cyber Physical Systems: A Survey for Machine Learning Security to Securing Machine Learning for CPS","created":"2021-02-14","cited_by_count":10,"area":null},{"id":"2107.01943","title":"When and How to Fool Explainable Models (and Humans) with Adversarial Examples","created":"2021-07-05","cited_by_count":10,"area":null},{"id":"2109.10870","title":"SoK: Machine Learning Governance","created":"2021-09-20","cited_by_count":10,"area":null},{"id":"2308.11336","title":"On the Opportunities and Challenges of Offline Reinforcement Learning for Recommender Systems","created":"2023-08-22","cited_by_count":10,"area":"offlinerl"},{"id":"2501.03562","title":"Rethinking Adversarial Attacks in Reinforcement Learning from Policy Distribution Perspective","created":"2025-01-07","cited_by_count":10,"area":"deeprl"},{"id":"2102.09677","title":"Training a Resilient Q-Network against Observational Interference","created":"2021-02-18","cited_by_count":9,"area":null},{"id":"2105.02480","title":"A Simple and Strong Baseline for Universal Targeted Attacks on Siamese Visual Tracking","created":"2021-05-06","cited_by_count":9,"area":null},{"id":"2106.08746","title":"Real-time Adversarial Perturbations against Deep Reinforcement Learning Policies: Attacks and Defenses","created":"2021-06-16","cited_by_count":9,"area":null},{"id":"2107.03050","title":"Controlled Caption Generation for Images Through Adversarial Attacks","created":"2021-07-07","cited_by_count":9,"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":"2205.09362","title":"Sparse Adversarial Attack in Multi-agent Reinforcement Learning","created":"2022-05-19","cited_by_count":8,"area":null},{"id":"2206.07188","title":"Defending Observation Attacks in Deep Reinforcement Learning via Detection and Denoising","created":"2022-06-14","cited_by_count":8,"area":null},{"id":"2401.02349","title":"A Survey Analyzing Generalization in Deep Reinforcement Learning","created":"2024-01-04","cited_by_count":8,"area":"deeprl"},{"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":"2503.20613","title":"State-Aware Perturbation Optimization for Robust Deep Reinforcement Learning","created":"2025-03-26","cited_by_count":8,"area":"deeprl"},{"id":"2212.11746","title":"Certified Policy Smoothing for Cooperative Multi-Agent Reinforcement Learning","created":"2022-12-22","cited_by_count":7,"area":null},{"id":"2305.17342","title":"Rethinking Adversarial Policies: A Generalized Attack Formulation and Provable Defense in RL","created":"2023-05-27","cited_by_count":7,"area":null},{"id":"2306.05873","title":"Detecting Adversarial Directions in Deep Reinforcement Learning to Make Robust Decisions","created":"2023-06-09","cited_by_count":7,"area":null},{"id":"2312.06436","title":"Reward Certification for Policy Smoothed Reinforcement Learning","created":"2023-12-11","cited_by_count":7,"area":null},{"id":"2405.11206","title":"Towards Robust Policy: Enhancing Offline Reinforcement Learning with Adversarial Attacks and Defenses","created":"2024-05-18","cited_by_count":7,"area":"offlinerl"},{"id":"2503.20844","title":"Robust Deep Reinforcement Learning in Robotics via Adaptive Gradient-Masked Adversarial Attacks","created":"2025-03-26","cited_by_count":7,"area":"deeprl"},{"id":"2605.23220","title":"WMAttack: Automated Attack Search for Adversarial Evaluation of World-Model Agents","created":"2026-05-22","cited_by_count":7,"area":"wm"},{"id":"2104.10262","title":"Network Defense is Not a Game","created":"2021-04-20","cited_by_count":6,"area":null},{"id":"2410.03376","title":"Mitigating Adversarial Perturbations for Deep Reinforcement Learning via Vector Quantization","created":"2024-10-04","cited_by_count":6,"area":"deeprl"},{"id":"2508.03768","title":"ORVIT: Near-Optimal Online Distributionally Robust Reinforcement Learning","created":"2025-08-05","cited_by_count":6,"area":"deeprl"},{"id":"2205.00807","title":"Deep-Attack over the Deep Reinforcement Learning","created":"2022-05-02","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":"2212.05337","title":"Targeted Adversarial Attacks on Deep Reinforcement Learning Policies via Model Checking","created":"2022-12-10","cited_by_count":5,"area":null},{"id":"2412.02795","title":"Hijacking Vision-and-Language Navigation Agents with Adversarial Environmental Attacks","created":"2024-12-03","cited_by_count":5,"area":null},{"id":"2109.07171","title":"Balancing detectability and performance of attacks on the control channel of Markov Decision Processes","created":"2021-09-15","cited_by_count":4,"area":null},{"id":"2402.02165","title":"Towards Optimal Adversarial Robust Q-learning with Bellman Infinity-error","created":"2024-02-03","cited_by_count":4,"area":"deeprl"},{"id":"2403.07933","title":"Corruption-Robust Offline Two-Player Zero-Sum Markov Games","created":"2024-03-04","cited_by_count":4,"area":null},{"id":"2404.04714","title":"Data Poisoning Attacks on Off-Policy Policy Evaluation Methods","created":"2024-04-06","cited_by_count":4,"area":"safety"},{"id":"2406.18062","title":"Breaking the Barrier: Enhanced Utility and Robustness in Smoothed DRL Agents","created":"2024-06-26","cited_by_count":4,"area":"deeprl"},{"id":"2407.15168","title":"Mitigating Deep Reinforcement Learning Backdoors in the Neural Activation Space","created":"2024-07-21","cited_by_count":4,"area":"deeprl"},{"id":"2410.10674","title":"Enhancing Robustness in Deep Reinforcement Learning: A Lyapunov Exponent Approach","created":"2024-10-14","cited_by_count":4,"area":"deeprl"},{"id":"2605.01950","title":"TRAP: Tail-aware Ranking Attack for World-Model Planning","created":"2026-05-03","cited_by_count":4,"area":"wm"},{"id":"2607.15207","title":"BadWAM: When World-Action Models Dream Right but Act Wrong","created":"2026-07-16","cited_by_count":4,"area":"wm"},{"id":"2102.06800","title":"Reinforcement Learning For Data Poisoning on Graph Neural Networks","created":"2021-02-12","cited_by_count":3,"area":null},{"id":"2103.02014","title":"Online Adversarial Attacks","created":"2021-03-02","cited_by_count":3,"area":null},{"id":"2210.11237","title":"Emerging Threats in Deep Learning-Based Autonomous Driving: A Comprehensive Survey","created":"2022-10-19","cited_by_count":3,"area":null},{"id":"2301.04299","title":"SoK: Adversarial Machine Learning Attacks and Defences in Multi-Agent Reinforcement Learning","created":"2023-01-11","cited_by_count":3,"area":null},{"id":"2301.11374","title":"Certifiably Robust Reinforcement Learning through Model-Based Abstract Interpretation","created":"2023-01-26","cited_by_count":3,"area":null},{"id":"2305.02605","title":"Toward Evaluating Robustness of Reinforcement Learning with Adversarial Policy","created":"2023-05-04","cited_by_count":3,"area":null},{"id":"2507.17070","title":"Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach","created":"2025-07-22","cited_by_count":3,"area":"deeprl"},{"id":"2210.16915","title":"Imitating Opponent to Win: Adversarial Policy Imitation Learning in Two-player Competitive Games","created":"2022-10-30","cited_by_count":2,"area":"offlinerl"},{"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":"2307.13642","title":"Safety Margins for Reinforcement Learning","created":"2023-07-25","cited_by_count":2,"area":null},{"id":"2406.03862","title":"Robust Deep Reinforcement Learning against Adversarial Behavior Manipulation","created":"2024-06-06","cited_by_count":2,"area":"deeprl"}],"next_cursor":"100"}