{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,9]],"date-time":"2025-05-09T04:40:11Z","timestamp":1746765611084,"version":"3.40.5"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2020YFA0713900"],"award-info":[{"award-number":["2020YFA0713900"]}]},{"name":"NSFC Project","award":["62192783"],"award-info":[{"award-number":["62192783"]}]},{"name":"Science Foundation of Zhejiang Sci-Tech University","award":["25232128-Y"],"award-info":[{"award-number":["25232128-Y"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans.Inform.Forensic Secur."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tifs.2025.3560203","type":"journal-article","created":{"date-parts":[[2025,4,11]],"date-time":"2025-04-11T17:55:59Z","timestamp":1744394159000},"page":"4679-4693","source":"Crossref","is-referenced-by-count":0,"title":["Grey-Box Adversarial Attack on Communication in Communicative Multi-Agent Reinforcement Learning"],"prefix":"10.1109","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2289-7336","authenticated-orcid":false,"given":"Xiao","family":"Ma","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology (School of Artificial Intelligence), Zhejiang Sci-Tech University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2499-4006","authenticated-orcid":false,"given":"Wu-Jun","family":"Li","sequence":"additional","affiliation":[{"name":"National Key Laboratory for Novel Software Technology, School of Computer Science, Nanjing University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","volume-title":"Proc. AAMAS","author":"Sunehag"},{"key":"ref2","first-page":"240","article-title":"Learning nearly decomposable value functions via communication minimization","volume-title":"Proc. ICLR","author":"Wang"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-023-06365-2"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2023.103905"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2017.12.001"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2021.3103062"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2012.2219061"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v26i1.8380"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2010.09.008"},{"key":"ref10","first-page":"2252","article-title":"Learning multiagent communication with backpropagation","volume-title":"Proc. NeurIPS","volume":"29","author":"Sukhbaatar"},{"key":"ref11","first-page":"9331","article-title":"Multi-agent reinforcement learning for networked system control","volume-title":"Proc. ICLR","author":"Chu"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2008.2009515"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2018.8619581"},{"key":"ref14","first-page":"2701","article-title":"VAIN: Attentional multi-agent predictive modeling","volume-title":"Proc. NeurIPS","volume":"30","author":"Hoshen"},{"key":"ref15","first-page":"1538","article-title":"TarMAC: Targeted multi-agent communication","volume-title":"Proc. ICML","author":"Das"},{"key":"ref16","first-page":"2137","article-title":"Learning to communicate with deep multi-agent reinforcement learning","volume-title":"Proc. NeurIPS","author":"Foerster"},{"key":"ref17","first-page":"7265","article-title":"Learning attentional communication for multi-agent cooperation","volume-title":"Proc. NeurIPS","author":"Jiang"},{"key":"ref18","first-page":"1","article-title":"Communication in multi-agent reinforcement learning: Intention sharing","volume-title":"Proc. ICLR","author":"Kim"},{"key":"ref19","first-page":"22069","article-title":"Learning individually inferred communication for multi-agent cooperation","volume-title":"Proc. NeurIPS","author":"Ding"},{"key":"ref20","first-page":"3911","article-title":"Learning when to communicate at scale in multiagent cooperative and competitive tasks","volume-title":"Proc. ICLR","author":"Singh"},{"key":"ref21","first-page":"17271","article-title":"Succinct and robust multi-agent communication with temporal message control","volume-title":"Proc. NeurIPS","author":"Zhang"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i10.26389"},{"key":"ref23","first-page":"1418","article-title":"Mis-spoke or mis-lead: Achieving robustness in multi-agent communicative reinforcement learning","volume-title":"Proc. AAMAS","author":"Xue"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/FG52635.2021.9667076"},{"key":"ref25","first-page":"12278","article-title":"Grey-box extraction of natural language models","volume-title":"Proc. ICML","author":"Zanella-B\u00e9guelin"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA58977.2023.00099"},{"key":"ref27","article-title":"Transferability in machine learning: From phenomena to black-box attacks using adversarial samples","author":"Papernot","year":"2016","journal-title":"arXiv:1605.07277"},{"key":"ref28","first-page":"1","article-title":"Adversarial attacks on neural network policies","volume-title":"Proc. ICLR","author":"Huang"},{"key":"ref29","first-page":"2448","article-title":"Grey-box adversarial attack on communication in multi-agent reinforcement learning","volume-title":"Proc. AAMAS","author":"Ma"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-09996-w"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5957"},{"key":"ref32","first-page":"1394","article-title":"The emergence of adversarial communication in multi-agent reinforcement learning","volume-title":"Proc. CoRL","author":"Blumenkamp"},{"key":"ref33","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":"ref34","first-page":"2842","article-title":"A theory of mind approach as test-time mitigation against emergent adversarial communication","volume-title":"Proc. AAMAS","author":"Piazza"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2024.3423428"},{"key":"ref36","first-page":"1","article-title":"Certifiably robust policy learning against adversarial multi-agent communication","volume-title":"Proc. ICLR","author":"Sun"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_15"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3052973.3053009"},{"key":"ref39","first-page":"1","article-title":"Explaining and harnessing adversarial examples","volume-title":"Proc. ICLR","author":"Goodfellow"},{"volume-title":"Distributed Algorithms","year":"1996","author":"Lynch","key":"ref40"},{"key":"ref41","article-title":"Buffered asynchronous SGD for Byzantine learning","volume":"24","author":"Yang","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref42","first-page":"23484","article-title":"Policy gradient method for robust reinforcement learning","volume-title":"Proc. ICML","author":"Wang"},{"key":"ref43","first-page":"6820","article-title":"On the global convergence rates of softmax policy gradient methods","volume-title":"Proc. ICML","author":"Mei"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-022-01920-6"},{"key":"ref45","first-page":"1675","article-title":"Gradient descent finds global minima of deep neural networks","volume-title":"Proc. ICML","author":"Du"},{"key":"ref46","article-title":"Implicit regularization in deep learning","author":"Neyshabur","year":"2017","journal-title":"arXiv:1709.01953"},{"key":"ref47","first-page":"376","article-title":"Spectral normalization for generative adversarial networks","volume-title":"Proc. ICLR","author":"Miyato"},{"key":"ref48","first-page":"1","article-title":"Intriguing properties of neural networks","volume-title":"Proc. ICLR","author":"Szegedy"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2019.2943467"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/SP46214.2022.9833783"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2020.3036801"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2024.3352913"},{"key":"ref53","first-page":"2186","article-title":"The StarCraft multi-agent challenge","volume-title":"Proc. AAMAS","author":"Samvelyan"},{"key":"ref54","first-page":"4292","article-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. ICML","author":"Rashid"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref56","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"}],"container-title":["IEEE Transactions on Information Forensics and Security"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10206\/10810755\/10963687.pdf?arnumber=10963687","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,9]],"date-time":"2025-05-09T04:21:25Z","timestamp":1746764485000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10963687\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/tifs.2025.3560203","relation":{},"ISSN":["1556-6013","1556-6021"],"issn-type":[{"type":"print","value":"1556-6013"},{"type":"electronic","value":"1556-6021"}],"subject":[],"published":{"date-parts":[[2025]]}}}