{"list":"other","total":51,"rows":[{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1610.02136","title":"A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks","created":"2016-10-07","cited_by_count":2385},{"id":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809},{"id":"2003.01690","title":"Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks","created":"2020-03-03","cited_by_count":1451},{"id":"1912.06680","title":"Dota 2 with Large Scale Deep Reinforcement Learning","created":"2019-12-13","cited_by_count":1103},{"id":"1602.02697","title":"Practical Black-Box Attacks against Machine Learning","created":"2016-02-08","cited_by_count":903},{"id":"1710.02298","title":"Rainbow: Combining Improvements in Deep Reinforcement Learning","created":"2017-10-06","cited_by_count":786},{"id":"1610.08401","title":"Universal adversarial perturbations","created":"2016-10-26","cited_by_count":784},{"id":"1712.01815","title":"Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm","created":"2017-12-05","cited_by_count":734},{"id":"2002.00444","title":"Deep Reinforcement Learning for Autonomous Driving: A Survey","created":"2020-02-02","cited_by_count":721},{"id":"1511.04508","title":"Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks","created":"2015-11-14","cited_by_count":678},{"id":"1703.02702","title":"Robust Adversarial Reinforcement Learning","created":"2017-03-08","cited_by_count":451},{"id":"1808.03314","title":"Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) Network","created":"2018-08-09","cited_by_count":420},{"id":"1712.07107","title":"Adversarial Examples: Attacks and Defenses for Deep Learning","created":"2017-12-19","cited_by_count":351},{"id":"1702.02284","title":"Adversarial Attacks on Neural Network Policies","created":"2017-02-08","cited_by_count":320},{"id":"1905.12784","title":"Intrinsic dimension of data representations in deep neural networks","created":"2019-05-29","cited_by_count":282},{"id":"2003.08938","title":"Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations","created":"2020-03-19","cited_by_count":238},{"id":"2310.10844","title":"Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks","created":"2023-10-16","cited_by_count":194},{"id":"1901.09184","title":"Action Robust Reinforcement Learning and Applications in Continuous Control","created":"2019-01-26","cited_by_count":174},{"id":"2101.08452","title":"Robust Reinforcement Learning on State Observations with Learned Optimal Adversary","created":"2021-01-21","cited_by_count":135},{"id":"1705.06452","title":"Delving into adversarial attacks on deep policies","created":"2017-05-18","cited_by_count":104},{"id":"1701.04143","title":"Vulnerability of Deep Reinforcement Learning to Policy Induction Attacks","created":"2017-01-16","cited_by_count":91},{"id":"1902.02186","title":"Distilling Policy Distillation","created":"2019-02-06","cited_by_count":84},{"id":"1810.01032","title":"Reinforcement Learning with Perturbed Rewards","created":"2018-10-02","cited_by_count":79},{"id":"2008.01976","title":"Robust Deep Reinforcement Learning through Adversarial Loss","created":"2020-08-05","cited_by_count":75},{"id":"2209.15179","title":"Physical Adversarial Attack meets Computer Vision: A Decade Survey","created":"2022-09-30","cited_by_count":67},{"id":"2001.09684","title":"Challenges and Countermeasures for Adversarial Attacks on Deep Reinforcement Learning","created":"2020-01-27","cited_by_count":61},{"id":"1607.04311","title":"Defensive Distillation is Not Robust to Adversarial Examples","created":"2016-07-14","cited_by_count":60},{"id":"2306.06123","title":"Adversarial attacks and defenses in explainable artificial intelligence: A survey","created":"2023-06-06","cited_by_count":48},{"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},{"id":"1909.02583","title":"Spatiotemporally Constrained Action Space Attacks on Deep Reinforcement Learning Agents","created":"2019-09-05","cited_by_count":25},{"id":"2006.05032","title":"Stealing Deep Reinforcement Learning Models for Fun and Profit","created":"2020-06-09","cited_by_count":24},{"id":"2102.05776","title":"Defense Against Reward Poisoning Attacks in Reinforcement Learning","created":"2021-02-10","cited_by_count":21},{"id":"2206.01888","title":"Reward Poisoning Attacks on Offline Multi-Agent Reinforcement Learning","created":"2022-06-04","cited_by_count":20},{"id":"2106.15860","title":"Understanding Adversarial Attacks on Observations in Deep Reinforcement Learning","created":"2021-06-30","cited_by_count":13},{"id":"2109.08776","title":"Exploring the Training Robustness of Distributional Reinforcement Learning against Noisy State Observations","created":"2021-09-17","cited_by_count":12},{"id":"2102.09677","title":"Training a Resilient Q-Network against Observational Interference","created":"2021-02-18","cited_by_count":9},{"id":"2106.08746","title":"Real-time Adversarial Perturbations against Deep Reinforcement Learning Policies: Attacks and Defenses","created":"2021-06-16","cited_by_count":9},{"id":"2402.06846","title":"System-level Analysis of Adversarial Attacks and Defenses on Intelligence in O-RAN based Cellular Networks","created":"2024-02-10","cited_by_count":8},{"id":"1806.02190","title":"Mitigation of Policy Manipulation Attacks on Deep Q-Networks with Parameter-Space Noise","created":"2018-06-04","cited_by_count":7},{"id":"2303.02725","title":"Local Environment Poisoning Attacks on Federated Reinforcement Learning","created":"2023-03-05","cited_by_count":6},{"id":"2312.07392","title":"ReRoGCRL: Representation-based Robustness in Goal-Conditioned Reinforcement Learning","created":"2023-12-12","cited_by_count":6},{"id":"2209.03540","title":"Reward Delay Attacks on Deep Reinforcement Learning","created":"2022-09-08","cited_by_count":5},{"id":"2008.06199","title":"Adversary Agnostic Robust Deep Reinforcement Learning","created":"2020-08-14","cited_by_count":4},{"id":"2402.09695","title":"Universal Black-Box Reward Poisoning Attack against Offline Reinforcement Learning","created":"2024-02-15","cited_by_count":4},{"id":"2403.18539","title":"Safe and Robust Reinforcement Learning: Principles and Practice","created":"2024-03-27","cited_by_count":4},{"id":"2210.02840","title":"Deep Reinforcement Learning based Evasion Generative Adversarial Network for Botnet Detection","created":"2022-10-06","cited_by_count":3},{"id":"2307.00907","title":"Enhancing the Robustness of QMIX against State-adversarial Attacks","created":"2023-07-03","cited_by_count":3},{"id":"2502.16133","title":"A Trust-Aware and Cost-Optimized Blockchain Oracle Selection Model with Deep Reinforcement Learning","created":"2025-02-22","cited_by_count":2},{"id":"2402.15617","title":"Reinforcement Learning-Based Approaches for Enhancing Security and Resilience in Smart Control: A Survey on Attack and Defense Methods","created":"2024-02-23","cited_by_count":1},{"id":"2409.16256","title":"A Critical Review of Safe Reinforcement Learning Techniques in Smart Grid Applications","created":"2024-09-24","cited_by_count":1}],"next_cursor":null}