{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T22:27:36Z","timestamp":1777501656683,"version":"3.51.4"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11246652","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"20418-20425","source":"Crossref","is-referenced-by-count":3,"title":["Robust Deep Reinforcement Learning in Robotics via Adaptive Gradient-Masked Adversarial Attacks"],"prefix":"10.1109","author":[{"given":"Zongyuan","family":"Zhang","sequence":"first","affiliation":[{"name":"The University of Hong Kong,Department of Computer Science,Hong Kong,China"}]},{"given":"Tianyang","family":"Duan","sequence":"additional","affiliation":[{"name":"The University of Hong Kong,Department of Computer Science,Hong Kong,China"}]},{"given":"Zheng","family":"Lin","sequence":"additional","affiliation":[{"name":"Fudan University,School of Computer Science,Shanghai,China"}]},{"given":"Dong","family":"Huang","sequence":"additional","affiliation":[{"name":"The University of Hong Kong,Department of Computer Science,Hong Kong,China"}]},{"given":"Zihan","family":"Fang","sequence":"additional","affiliation":[{"name":"Fudan University,School of Computer Science,Shanghai,China"}]},{"given":"Zekai","family":"Sun","sequence":"additional","affiliation":[{"name":"The University of Hong Kong,Department of Computer Science,Hong Kong,China"}]},{"given":"Ling","family":"Xiong","sequence":"additional","affiliation":[{"name":"Xihua University,School of Computer and Software Engineering,Chengdu,China"}]},{"given":"Hongbin","family":"Liang","sequence":"additional","affiliation":[{"name":"Southwest Jiaotong University,School of Transportation and Logistics,Chengdu,China"}]},{"given":"Heming","family":"Cui","sequence":"additional","affiliation":[{"name":"The University of Hong Kong,Department of Computer Science,Hong Kong,China"}]},{"given":"Yong","family":"Cui","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Computer Science and Technology,Beijing,China"}]},{"given":"Yue","family":"Gao","sequence":"additional","affiliation":[{"name":"Fudan University,School of Computer Science,Shanghai,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2022.3211206"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.36227\/techrxiv.173220709.92421649\/v1","article-title":"IC3M: In-Car Multimodal Multi-Object Monitoring for Abnormal Status of Both Driver and Passengers","author":"Fang","year":"2024"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3359040"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/s23073762"},{"key":"ref5","first-page":"432","article-title":"Softgym: Benchmarking deep reinforcement learning for deformable object manipulation","volume-title":"Conf. Robot Learn","author":"Lin"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10890540"},{"issue":"200","key":"ref7","first-page":"1","article-title":"Distributionally robust model-based offline reinforcement learning with near-optimal sample complexity","volume":"25","author":"Shi","year":"2024","journal-title":"J. Mach. Learn. Res."},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2015.2471196"},{"key":"ref9","article-title":"Robust deep reinforcement learning through adversarial attacks and training: A survey","author":"Schott","year":"2024"},{"key":"ref10","article-title":"Two heads are better than one: Robust learning meets multi-branch models","author":"Huang","year":"2022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00406"},{"key":"ref12","article-title":"Towards Deep Learning Models Resistant to Adversarial Attacks","author":"Madry","year":"2017"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00741"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3480519"},{"key":"ref15","article-title":"Content-based unrestricted adversarial attack","volume":"36","author":"Chen","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref16","first-page":"26 156","article-title":"Robust Deep Reinforcement Learning through Adversarial Loss","volume":"34","author":"Oikarinen","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3127960"},{"key":"ref18","article-title":"Explaining and Harnessing Adversarial Examples","author":"Goodfellow","year":"2014"},{"key":"ref19","article-title":"Fast Is Better Than Free: Revisiting Adversarial Training","author":"Wong","year":"2020"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-023-04532-5"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01585"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00957"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00284"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00444"},{"key":"ref25","article-title":"Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attacks","author":"Lin","year":"2019"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2021.3111139"},{"key":"ref27","article-title":"Adversarial Attacks on Neural Network Policies","author":"Huang","year":"2017"},{"key":"ref28","article-title":"Robust Deep Reinforcement Learning with Adversarial Attacks","author":"Pattanaik","year":"2017"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/525"},{"key":"ref30","article-title":"Toward Evaluating Robustness of Deep Reinforcement Learning with Continuous Control","volume-title":"Int. Conf. Learn. Represent","author":"Weng"},{"key":"ref31","first-page":"21 024","article-title":"Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations","volume":"33","author":"Zhang","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref32","article-title":"Reinforcement learning: An introduction","author":"Sutton","year":"2018","journal-title":"Bradford Book"},{"key":"ref33","article-title":"High-dimensional Continuous Control Using Generalized Advantage Estimation","author":"Schulman","year":"2015"},{"issue":"2","key":"ref34","first-page":"895","article-title":"Per-contact iteration method for solving contact dynamics","volume-title":"IEEE Robot. Autom. Lett.","volume":"3","author":"Hwangbo","year":"2018"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.12794\/metadc1505267"},{"key":"ref36","article-title":"Ensemble Adversarial Training: Attacks and Defenses","author":"Tram\u00e8r","year":"2017"},{"key":"ref37","first-page":"7472","article-title":"Theoretically Principled Trade-off Between Robustness and Accuracy","volume-title":"Int. Conf. Mach. Learn","author":"Zhang"},{"key":"ref38","article-title":"Adv-bnn: Improved Adversarial Defense through Robust Bayesian Neural Network","author":"Liu","year":"2018"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Hangzhou, China","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11246652.pdf?arnumber=11246652","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:36:55Z","timestamp":1766061415000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11246652\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11246652","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}