{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T15:24:49Z","timestamp":1784301889904,"version":"3.55.0"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21A20444"],"award-info":[{"award-number":["U21A20444"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFB3107600"],"award-info":[{"award-number":["2023YFB3107600"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans.Inform.Forensic Secur."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tifs.2024.3423428","type":"journal-article","created":{"date-parts":[[2024,7,4]],"date-time":"2024-07-04T17:30:25Z","timestamp":1720114225000},"page":"6824-6839","source":"Crossref","is-referenced-by-count":18,"title":["Safe Multi-Agent Reinforcement Learning for Wireless Applications Against Adversarial Communications"],"prefix":"10.1109","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3880-5069","authenticated-orcid":false,"given":"Zefang","family":"Lv","sequence":"first","affiliation":[{"name":"Department of Informatics and Communication Engineering and the Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2402-611X","authenticated-orcid":false,"given":"Liang","family":"Xiao","sequence":"additional","affiliation":[{"name":"Department of Informatics and Communication Engineering and the Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yifan","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Informatics and Communication Engineering and the Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0417-7968","authenticated-orcid":false,"given":"Haoyu","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence, Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7333-9975","authenticated-orcid":false,"given":"Xiangyang","family":"Ji","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM54140.2023.10436722"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2022.3153316"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2023.3268082"},{"key":"ref4","first-page":"1394","article-title":"The emergence of adversarial communication in multi-agent reinforcement learning","volume-title":"Proc. Conf. Robot Learn. (CoRL)","author":"Blumenkamp"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3188833"},{"key":"ref6","first-page":"22069","article-title":"Learning individually inferred communication for multi-agent cooperation","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Ding"},{"key":"ref7","first-page":"17271","article-title":"Succinct and robust multi-agent communication with temporal message control","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Zhang"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3104633"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2021.3120050"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.3036962"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2021.3103062"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2022.3170308"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3303253"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2021.3097290"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2019.2904486"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2024.3374215"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMLCN.2023.3334236"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2022.3229033"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2022.3220870"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3087248"},{"key":"ref22","first-page":"1883","article-title":"Adversarial policy training against deep reinforcement learning","volume-title":"Proc. 30th USENIX Secur. Symp.","author":"Wu"},{"key":"ref23","first-page":"7974","article-title":"Policy teaching via environment poisoning: Training-time adversarial attacks against reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rakhsha"},{"key":"ref24","first-page":"1","article-title":"c-MBA: Adversarial attack for cooperative MARL using learned dynamics model","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Pham"},{"key":"ref25","first-page":"24414","article-title":"Robust policy learning over multiple uncertainty sets","volume-title":"Porc. Int. Conf. Mach. Learn. (ICML)","author":"Xie"},{"key":"ref26","first-page":"2817","article-title":"Robust adversarial reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pinto"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6086"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2022.3207429"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00767"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM54140.2023.10437779"},{"key":"ref31","first-page":"21024","article-title":"Robust deep reinforcement learning against adversarial perturbations on state observations","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Zhang"},{"key":"ref32","first-page":"1","article-title":"Robust multi-agent Q-learning in cooperative games with adversaries","volume-title":"Proc. AAAI Conf. Artif. Intell.","author":"Nisioti"},{"key":"ref33","first-page":"1418","article-title":"Mis-spoke or mis-lead: Achieving robustness in multi-agent communicative reinforcement learning","volume-title":"Proc. Int. Conf. Auton. Agents Multi-Agent Syst. (AAMAS)","author":"Xue"},{"key":"ref34","article-title":"Gaussian process based message filtering for robust multi-agent cooperation in the presence of adversarial communication","author":"Mitchell","year":"2020","journal-title":"arXiv:2012.00508"},{"key":"ref35","first-page":"1055","article-title":"Learning and testing resilience in cooperative multi-agent systems","volume-title":"Proc. Int. Conf. Auton. Agents Multi-Agent Syst. (AAMAS)","author":"Phan"},{"key":"ref36","first-page":"1","article-title":"Certifiably robust policy learning against adversarial multi-agent communication","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Sun"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014213"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i13.17348"},{"key":"ref39","first-page":"22056","article-title":"On the stability and convergence of robust adversarial reinforcement learning: A case study on linear quadratic systems","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Zhang"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2015.2492556"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2789466"},{"key":"ref42","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"}],"container-title":["IEEE Transactions on Information Forensics and Security"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10206\/10319981\/10584557.pdf?arnumber=10584557","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,19]],"date-time":"2024-07-19T05:55:56Z","timestamp":1721368556000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10584557\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/tifs.2024.3423428","relation":{},"ISSN":["1556-6013","1556-6021"],"issn-type":[{"value":"1556-6013","type":"print"},{"value":"1556-6021","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}