{"list":"other","total":49,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"1901.08573","title":"Theoretically Principled Trade-off between Robustness and Accuracy","created":"2019-01-24","cited_by_count":1517},{"id":"1705.10528","title":"Constrained Policy Optimization","created":"2017-05-30","cited_by_count":983},{"id":"1705.07204","title":"Ensemble Adversarial Training: Attacks and Defenses","created":"2017-05-19","cited_by_count":840},{"id":"2001.03994","title":"Fast is better than free: Revisiting adversarial training","created":"2020-01-12","cited_by_count":727},{"id":"1803.06978","title":"Improving Transferability of Adversarial Examples with Input Diversity","created":"2018-03-19","cited_by_count":599},{"id":"1904.02884","title":"Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attacks","created":"2019-04-05","cited_by_count":442},{"id":"1908.06281","title":"Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attacks","created":"2019-08-17","cited_by_count":355},{"id":"1702.02284","title":"Adversarial Attacks on Neural Network Policies","created":"2017-02-08","cited_by_count":320},{"id":"1810.00069","title":"Adversarial Attacks and Defences: A Survey","created":"2018-09-28","cited_by_count":259},{"id":"2003.08938","title":"Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations","created":"2020-03-19","cited_by_count":238},{"id":"1703.06748","title":"Tactics of Adversarial Attack on Deep Reinforcement Learning Agents","created":"2017-03-08","cited_by_count":166},{"id":"2102.00436","title":"Admix: Enhancing the Transferability of Adversarial Attacks","created":"2021-01-31","cited_by_count":156},{"id":"1712.03632","title":"Robust Deep Reinforcement Learning with Adversarial Attacks","created":"2017-12-11","cited_by_count":154},{"id":"2310.12567","title":"Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark","created":"2023-10-19","cited_by_count":143},{"id":"2108.00401","title":"Advances in adversarial attacks and defenses in computer vision: A survey","created":"2021-08-01","cited_by_count":127},{"id":"2011.07215","title":"SoftGym: Benchmarking Deep Reinforcement Learning for Deformable Object Manipulation","created":"2020-11-14","cited_by_count":121},{"id":"2303.15991","title":"Efficient Parallel Split Learning over Resource-constrained Wireless Edge Networks","created":"2023-03-26","cited_by_count":95},{"id":"2305.08192","title":"Diffusion Models for Imperceptible and Transferable Adversarial Attack","created":"2023-05-14","cited_by_count":94},{"id":"2208.05767","title":"Distributionally Robust Model-Based Offline Reinforcement Learning with Near-Optimal Sample Complexity","created":"2022-08-11","cited_by_count":87},{"id":"2008.01976","title":"Robust Deep Reinforcement Learning through Adversarial Loss","created":"2020-08-05","cited_by_count":75},{"id":"2305.10665","title":"Content-based Unrestricted Adversarial Attack","created":"2023-05-18","cited_by_count":73},{"id":"1810.01279","title":"Adv-BNN: Improved Adversarial Defense through Robust Bayesian Neural Network","created":"2018-10-01","cited_by_count":69},{"id":"2403.13101","title":"AdaptSFL: Adaptive Split Federated Learning in Resource-constrained Edge Networks","created":"2024-03-19","cited_by_count":64},{"id":"2407.00952","title":"SplitLoRA: A Split Parameter-Efficient Fine-Tuning Framework for Large Language Models","created":"2024-07-01","cited_by_count":62},{"id":"2001.09684","title":"Challenges and Countermeasures for Adversarial Attacks on Deep Reinforcement Learning","created":"2020-01-27","cited_by_count":61},{"id":"2108.09034","title":"AdvDrop: Adversarial Attack to DNNs by Dropping Information","created":"2021-08-20","cited_by_count":56},{"id":"2404.06448","title":"Automated Federated Pipeline for Parameter-Efficient Fine-Tuning of Large Language Models","created":"2024-04-09","cited_by_count":49},{"id":"2404.06345","title":"AgentsCoDriver: Large Language Model Empowered Collaborative Driving with Lifelong Learning","created":"2024-04-09","cited_by_count":40},{"id":"2311.01483","title":"FedSN: A Federated Learning Framework over Heterogeneous LEO Satellite Networks","created":"2023-11-02","cited_by_count":38},{"id":"2412.07197","title":"Hierarchical Split Federated Learning: Convergence Analysis and System Optimization","created":"2024-12-10","cited_by_count":38},{"id":"2105.10304","title":"Exploring Misclassifications of Robust Neural Networks to Enhance Adversarial Attacks","created":"2021-05-21","cited_by_count":33},{"id":"2308.08896","title":"Optimal Resource Allocation for U-Shaped Parallel Split Learning","created":"2023-08-17","cited_by_count":33},{"id":"2502.05224","title":"A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations","created":"2025-02-06","cited_by_count":27},{"id":"2403.16460","title":"FedAC: An Adaptive Clustered Federated Learning Framework for Heterogeneous Data","created":"2024-03-25","cited_by_count":25},{"id":"2408.03624","title":"AgentsCoMerge: Large Language Model Empowered Collaborative Decision Making for Ramp Merging","created":"2024-08-07","cited_by_count":22},{"id":"2501.01293","title":"LEO-Split: A Semi-Supervised Split Learning Framework over LEO Satellite Networks","created":"2025-01-02","cited_by_count":22},{"id":"2409.13503","title":"SatFed: A Resource-Efficient LEO Satellite-Assisted Heterogeneous Federated Learning Framework","created":"2024-09-20","cited_by_count":21},{"id":"2410.02592","title":"IC3M: In-Car Multimodal Multi-object Monitoring for Abnormal Status of Both Driver and Passengers","created":"2024-10-03","cited_by_count":20},{"id":"2410.00392","title":"MERIT: Multimodal Wearable Vital Sign Waveform Monitoring","created":"2024-10-01","cited_by_count":16},{"id":"2206.02670","title":"Robust Adversarial Attacks Detection based on Explainable Deep Reinforcement Learning For UAV Guidance and Planning","created":"2022-06-06","cited_by_count":13},{"id":"2307.09763","title":"Towards Building More Robust Models with Frequency Bias","created":"2023-07-19","cited_by_count":12},{"id":"2502.18474","title":"A Contemporary Survey of Large Language Model Assisted Program Analysis","created":"2025-02-05","cited_by_count":11},{"id":"2208.08083","title":"Two Heads are Better than One: Robust Learning Meets Multi-branch Models","created":"2022-08-17","cited_by_count":1}],"next_cursor":null}