{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T17:19:30Z","timestamp":1774718370641,"version":"3.50.1"},"reference-count":65,"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:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3438803","type":"journal-article","created":{"date-parts":[[2024,8,5]],"date-time":"2024-08-05T17:57:27Z","timestamp":1722880647000},"page":"170437-170450","source":"Crossref","is-referenced-by-count":1,"title":["Robust Multi-Agent Communication via Diffusion-Based Message Denoising"],"prefix":"10.1109","volume":"12","author":[{"given":"Jian","family":"Chen","sequence":"first","affiliation":[{"name":"Naval Aviation University, Yantai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8115-601X","authenticated-orcid":false,"given":"Jian-Yin","family":"Zhao","sequence":"additional","affiliation":[{"name":"Naval Aviation University, Yantai, China"}]},{"given":"Wen-Fei","family":"Zhao","sequence":"additional","affiliation":[{"name":"Naval Aviation University, Yantai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5329-2529","authenticated-orcid":false,"given":"Yu-Feng","family":"Qin","sequence":"additional","affiliation":[{"name":"Naval Aviation University, Yantai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7301-824X","authenticated-orcid":false,"given":"Hong","family":"Ji","sequence":"additional","affiliation":[{"name":"Naval Aviation University, Yantai, China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"A survey of progress on cooperative multi-agent reinforcement learning in open environment","author":"Yuan","year":"2023","journal-title":"arXiv:2312.01058"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s43154-022-00091-8"},{"key":"ref3","article-title":"Dota 2 with large scale deep reinforcement learning","author":"Berner","year":"2019","journal-title":"arXiv:1912.06680"},{"key":"ref4","first-page":"464","article-title":"Multi-agent reinforcement learning in sequential social Dilemmas","volume-title":"Proc. Int. Conf. Auto. Agents Multiagent Syst. (AAMAS)","author":"Leibo"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-023-09633-6"},{"key":"ref6","first-page":"3230","article-title":"Efficient communication in multi-agent reinforcement learning via variance based control","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"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.","author":"Zhang"},{"key":"ref8","first-page":"22069","article-title":"Learning individually inferred communication for multi-agent cooperation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ding"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/82"},{"key":"ref10","first-page":"2137","article-title":"Learning to communicate with deep multi-agent reinforcement learning","volume-title":"Proc. Conf. Adv. Neural Inf. Process. Syst.","author":"Foerster"},{"key":"ref11","article-title":"Learning nearly decomposable value functions via communication minimization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wang"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i9.21179"},{"key":"ref13","first-page":"1538","article-title":"TarMAC: Targeted multi-agent communication","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","volume":"97","author":"Das"},{"key":"ref14","first-page":"1020","article-title":"Efficient multi-agent communication via self-supervised information aggregation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Guan"},{"key":"ref15","article-title":"RoMFAC: A robust mean-field actor-critic reinforcement learning against adversarial perturbations on states","author":"Zhou","year":"2022","journal-title":"arXiv:2205.07229"},{"key":"ref16","first-page":"2817","article-title":"Robust adversarial reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pinto"},{"key":"ref17","first-page":"10571","article-title":"Robust multi-agent reinforcement learning with model uncertainty","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3390\/make4010013"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812420"},{"key":"ref20","article-title":"Robust reinforcement learning using adversarial populations","author":"Vinitsky","year":"2020","journal-title":"arXiv:2008.01825"},{"key":"ref21","first-page":"1418","article-title":"Mis-spoke or mis-lead: Achieving robustness in multi-agent communicative reinforcement learning","volume-title":"Proc. Int. Conf. Auto. Agents Multiagent Syst.","author":"Xue"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-023-3853-y"},{"key":"ref23","article-title":"Certifiably robust policy learning against adversarial communication in multi-agent systems","author":"Sun","year":"2022","journal-title":"arXiv:2206.10158"},{"key":"ref24","article-title":"Detecting adversarial attacks on neural network policies with visual foresight","author":"Lin","year":"2017","journal-title":"arXiv:1710.00814"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref26","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein"},{"key":"ref27","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NIPS","volume":"33","author":"Ho"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6114"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00286"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261988"},{"key":"ref33","first-page":"4328","article-title":"Diffusion-lM improves controllable text generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref34","first-page":"964","article-title":"Multi-agent graph-attention communication and teaming","volume-title":"Proc. 20th Int. Conf. Auto. Agents MultiAgent Syst.","author":"Niu"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-19-7784-8_10"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794293"},{"key":"ref37","first-page":"21024","article-title":"Robust deep reinforcement learning against adversarial perturbations on state observations","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"33","author":"Zhang"},{"key":"ref38","first-page":"26156","article-title":"Robust deep reinforcement learning through adversarial loss","volume-title":"Proc. 35th Int. Conf. Neural Inf. Process. Syst.","author":"Oikarinen"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i10.26388"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00022"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014213"},{"key":"ref42","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. NIPS","author":"Lowe"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i13.17348"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref45","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. NIPS","volume":"35","author":"Saharia"},{"key":"ref46","first-page":"9902","article-title":"Planning with diffusion for flexible behavior synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Janner"},{"key":"ref47","first-page":"20725","article-title":"Adaptdiffuser: Diffusion models as adaptive self-evolving planners","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liang"},{"key":"ref48","first-page":"26087","article-title":"MetaDiffuser: Diffusion model as conditional planner for offline meta-RL","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ni"},{"key":"ref49","article-title":"MADiff: Offline multi-agent learning with diffusion models","author":"Zhu","year":"2023","journal-title":"arXiv:2305.17330"},{"key":"ref50","article-title":"Diffusion models for reinforcement learning: A survey","author":"Zhu","year":"2023","journal-title":"arXiv:2311.01223"},{"key":"ref51","article-title":"Diffusion policies as an expressive policy class for offline reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wang"},{"key":"ref52","article-title":"Imitating human behaviour with diffusion models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Pearce"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.028"},{"key":"ref54","article-title":"Synthetic experience replay","volume-title":"Proc. Workshop Reincarnating Reinforcement Learn. Int. Conf. Learn. Represent.","author":"Lu"},{"key":"ref55","article-title":"Diffusion model is an effective planner and data synthesizer for multi-task reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"He"},{"key":"ref56","article-title":"Flow to better: Offline preference-based reinforcement learning via preferred trajectory generation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhang"},{"key":"ref57","article-title":"Fixing data augmentation to improve adversarial robustness","author":"Rebuffi","year":"2021","journal-title":"arXiv:2103.01946"},{"key":"ref58","first-page":"36246","article-title":"Better diffusion models further improve adversarial training","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","volume":"202","author":"Wang"},{"key":"ref59","first-page":"12062","article-title":"Adversarial purification with score-based generative models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yoon"},{"key":"ref60","first-page":"16805","article-title":"Diffusion models for adversarial purification","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Nie"},{"key":"ref61","article-title":"Guided diffusion model for adversarial purification","author":"Wang","year":"2022","journal-title":"arXiv:2205.14969"},{"key":"ref62","article-title":"Benchmarking multi-agent deep reinforcement learning algorithms in cooperative tasks","volume-title":"Proc. Neural Inf. Process. Syst. Track Datasets Benchmarks","author":"Papoudakis"},{"key":"ref63","article-title":"The StarCraft multi-agent challenge","volume-title":"Proc. Int. Conf. Auton. Agents Multiagent Syst. (AAMAS)","author":"Samvelyan"},{"key":"ref64","article-title":"Explaining and harnessing adversarial examples","author":"Goodfellow","year":"2014","journal-title":"arXiv:1412.6572"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.06083"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10623476.pdf?arnumber=10623476","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:13:00Z","timestamp":1732666380000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10623476\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3438803","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}