{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:17:50Z","timestamp":1774419470074,"version":"3.50.1"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890540","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":5,"title":["Rethinking Adversarial Attacks in Reinforcement Learning from Policy Distribution Perspective"],"prefix":"10.1109","author":[{"given":"Tianyang","family":"Duan","sequence":"first","affiliation":[{"name":"The University of Hong Kong,Department of Computer Science,Hong Kong,China"}]},{"given":"Zongyuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"The University of Hong Kong,Department of Computer Science,Hong Kong,China"}]},{"given":"Zheng","family":"Lin","sequence":"additional","affiliation":[{"name":"The University of Hong Kong,Department of Electrical and Electronic Engineering,Hong Kong,China"}]},{"given":"Yue","family":"Gao","sequence":"additional","affiliation":[{"name":"Fudan University,School of Computer Science,China"}]},{"given":"Ling","family":"Xiong","sequence":"additional","affiliation":[{"name":"Xihua University,School of Computer and Software Engineering,Chengdu,China"}]},{"given":"Yong","family":"Cui","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Computer Science and Technology,Beijing,China"}]},{"given":"Hongbin","family":"Liang","sequence":"additional","affiliation":[{"name":"Southwest Jiaotong University,School of Transportation and Logistics,Chengdu,China"}]},{"given":"Xianhao","family":"Chen","sequence":"additional","affiliation":[{"name":"The University of Hong Kong,Department of Electrical and Electronic Engineering,Hong Kong,China"}]},{"given":"Heming","family":"Cui","sequence":"additional","affiliation":[{"name":"The University of Hong Kong,Department of Computer Science,Hong Kong,China"}]},{"given":"Dong","family":"Huang","sequence":"additional","affiliation":[{"name":"The University of Hong Kong,Department of Computer Science,Hong Kong,China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"11480","article-title":"Crpo: A new approach for safe reinforcement learning with convergence guarantee","volume-title":"International Conference on Machine Learning","author":"Xu"},{"key":"ref2","first-page":"22","article-title":"Constrained policy optimization","volume-title":"International conference on machine learning","author":"Achiam"},{"key":"ref3","article-title":"Cup: A conservative update policy algorithm for safe reinforcement learning","author":"Yang","year":"2022"},{"key":"ref4","article-title":"Deep reinforcement learning for real autonomous mobile robot navigation in indoor environments","author":"Surmann","year":"2020"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.26599\/TST.2021.9010012"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2023.3299275"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2023.113670"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-06116-1"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-95892-3_41"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2015.2471196"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3459991"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-019-1211-x"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1049\/cit2.12028"},{"key":"ref14","article-title":"Robust deep reinforcement learning with adversarial attacks","author":"Pattanaik","year":"2017"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i7.26009"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2019.2890858"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00930"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892966"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6047"},{"key":"ref20","article-title":"Robust reinforcement learning on state observations with learned optimal adversary","author":"Zhang","year":"2021"},{"key":"ref21","first-page":"26156","article-title":"Robust deep reinforcement learning through adversarial loss","volume":"34","author":"Oikarinen","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3207346"},{"key":"ref23","article-title":"Adversarial attacks on neural network policies","author":"Huang","year":"2017"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/525"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCOM.1967.1089532"},{"key":"ref26","article-title":"Explaining and harnessing adversarial examples","author":"Goodfellow","year":"2014"},{"key":"ref27","article-title":"Towards deep learning models resistant to adversarial attacks","author":"Madry","year":"2017"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00406"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00957"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00284"},{"key":"ref31","article-title":"Nesterov accelerated gradient and scale invariance for adversarial attacks","author":"Lin","year":"2019"},{"key":"ref32","article-title":"Toward evaluating robustness of deep reinforcement learning with continuous control","volume-title":"International Conference on Learning Representations","author":"Weng"},{"key":"ref33","article-title":"Online robustness training for deep reinforcement learning","author":"Fischer","year":"2019"},{"key":"ref34","first-page":"21024","article-title":"Robust deep reinforcement learning against adversarial perturbations on state observations","volume":"33","author":"Zhang","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref36","article-title":"Safety gymnasium: A unified safe reinforcement learning benchmark","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track","author":"Ji"},{"key":"ref37","article-title":"Trust region policy optimization","author":"Schulman","year":"2015"},{"key":"ref38","first-page":"7472","article-title":"Theoretically principled trade-off between robustness and accuracy","volume-title":"International conference on machine learning","author":"Zhang"},{"key":"ref39","article-title":"Adv-bnn: Improved adversarial defense through robust bayesian neural network","author":"Liu","year":"2018"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/BF00532240"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10890540.pdf?arnumber=10890540","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:59Z","timestamp":1774416179000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890540\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890540","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}