{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T03:58:57Z","timestamp":1743047937962,"version":"3.40.3"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031212024"},{"type":"electronic","value":"9783031212031"}],"license":[{"start":{"date-parts":[[2022,11,12]],"date-time":"2022-11-12T00:00:00Z","timestamp":1668211200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,11,12]],"date-time":"2022-11-12T00:00:00Z","timestamp":1668211200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-21203-1_21","type":"book-chapter","created":{"date-parts":[[2022,11,11]],"date-time":"2022-11-11T07:35:25Z","timestamp":1668152125000},"page":"347-363","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Weaponizing Actions in\u00a0Multi-Agent Reinforcement Learning: Theoretical and\u00a0Empirical Study on\u00a0Security and\u00a0Robustness"],"prefix":"10.1007","author":[{"given":"Tongtong","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joe","family":"McCalmon","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Md Asifur","family":"Rahman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cameron","family":"Lischke","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Talal","family":"Halabi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sarra","family":"Alqahtani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,11,12]]},"reference":[{"issue":"6","key":"21_CR1","doi-asserted-by":"publisher","first-page":"126","DOI":"10.1109\/MCOM.2015.7120028","volume":"53","author":"M Amoozadeh","year":"2015","unstructured":"Amoozadeh, M., et al.: Security vulnerabilities of connected vehicle streams and their impact on cooperative driving. IEEE Commun. Mag. 53(6), 126\u2013132 (2015). https:\/\/doi.org\/10.1109\/MCOM.2015.7120028","journal-title":"IEEE Commun. Mag."},{"key":"21_CR2","unstructured":"Bagnell, J.A.D.: An invitation to imitation. Technical report. CMU-RI-TR-15-08, Carnegie Mellon University, Pittsburgh, PA (2015)"},{"key":"21_CR3","doi-asserted-by":"publisher","unstructured":"Bakakeu, J., Kisskalt, D., Franke, J., Baer, S., Klos, H.H., Peschke, J.: Multi-agent reinforcement learning for the energy optimization of cyber-physical production systems. In: 2020 IEEE Canadian Conference on Electrical and Computer Engineering (CCECE), pp. 1\u20138 (2020). https:\/\/doi.org\/10.1109\/CCECE47787.2020.9255795","DOI":"10.1109\/CCECE47787.2020.9255795"},{"key":"21_CR4","doi-asserted-by":"publisher","unstructured":"Dadras, S., Dadras, S., Winstead, C.: Collaborative attacks on autonomous vehicle platooning. In: 2018 IEEE 61st International Midwest Symposium on Circuits and Systems (MWSCAS), pp. 464\u2013467 (2018). https:\/\/doi.org\/10.1109\/MWSCAS.2018.8624026","DOI":"10.1109\/MWSCAS.2018.8624026"},{"key":"21_CR5","doi-asserted-by":"crossref","unstructured":"Foerster, J.N., Farquhar, G., Afouras, T., Nardelli, N., Whiteson, S.: Counterfactual multi-agent policy gradients. In: AAAI (2018)","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"21_CR6","unstructured":"Fu, J., Luo, K., Levine, S.: Learning robust rewards with adversarial inverse reinforcement learning (2018)"},{"key":"21_CR7","doi-asserted-by":"publisher","unstructured":"Higgins, F., Tomlinson, A., Martin, K.M.: Survey on security challenges for swarm robotics. In: 2009 Fifth International Conference on Autonomic and Autonomous Systems, pp. 307\u2013312 (2009). DOI: https:\/\/doi.org\/10.1109\/ICAS.2009.62","DOI":"10.1109\/ICAS.2009.62"},{"key":"21_CR8","unstructured":"Huang, S., Papernot, N., Goodfellow, I., Duan, Y., Abbeel, P.: Adversarial attacks on neural network policies (2017)"},{"key":"21_CR9","unstructured":"Jaques, N., et al.: Social influence as intrinsic motivation for multi-agent deep reinforcement learning (2019)"},{"key":"21_CR10","unstructured":"Jo, U., Jo, T., Kim, W., Yoon, I., Lee, D., Lee, S.: Cooperative multi-agent reinforcement learning framework for scalping trading (2019)"},{"key":"21_CR11","unstructured":"Kos, J., Song, D.: Delving into adversarial attacks on deep policies (2017)"},{"key":"21_CR12","unstructured":"Levine, S.: Reinforcement learning and control as probabilistic inference: tutorial and review (2018)"},{"key":"21_CR13","doi-asserted-by":"crossref","unstructured":"Lin, J., Dzeparoska, K., Zhang, S.Q., Leon-Garcia, A., Papernot, N.: On the robustness of cooperative multi-agent reinforcement learning (2020)","DOI":"10.1109\/SPW50608.2020.00027"},{"key":"21_CR14","unstructured":"Lin, Y.C., Hong, Z.W., Liao, Y.H., Shih, M.L., Liu, M.Y., Sun, M.: Tactics of adversarial attack on deep reinforcement learning agents (2019)"},{"key":"21_CR15","unstructured":"Liu, M., et al.: Multi-agent interactions modeling with correlated policies (2020)"},{"key":"21_CR16","unstructured":"Lowe, R., Wu, Y., Tamar, A., Harb, J., Abbeel, P., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, pp. 6382\u20136393. NIPS 2017, Curran Associates Inc., Red Hook, NY, USA (2017)"},{"key":"21_CR17","doi-asserted-by":"publisher","unstructured":"Peake, A., McCalmon, J., Raiford, B., Liu, T., Alqahtani, S.: Multi-agent reinforcement learning for cooperative adaptive cruise control. In: 2020 IEEE 32nd International Conference on Tools with Artificial Intelligence (ICTAI), pp. 15\u201322 (2020). https:\/\/doi.org\/10.1109\/ICTAI50040.2020.00013","DOI":"10.1109\/ICTAI50040.2020.00013"},{"key":"21_CR18","unstructured":"Rashid, T., Samvelyan, M., de Witt, C.S., Farquhar, G., Foerster, J., Whiteson, S.: Qmix: monotonic value function factorisation for deep multi-agent reinforcement learning (2018)"},{"key":"21_CR19","doi-asserted-by":"publisher","unstructured":"Shapley, L.S.: Stochastic games. Proc. National Acad. Sci. 39(10), 1095\u20131100 (1953). https:\/\/doi.org\/10.1073\/pnas.39.10.1095, https:\/\/www.pnas.org\/content\/39\/10\/1095","DOI":"10.1073\/pnas.39.10.1095"},{"key":"21_CR20","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. A Bradford Book, Cambridge, MA, USA (2018)"},{"key":"21_CR21","doi-asserted-by":"crossref","unstructured":"Tang, Y.C.: Towards learning multi-agent negotiations via self-play (2020)","DOI":"10.1109\/ICCVW.2019.00297"},{"key":"21_CR22","unstructured":"Tian, Z., et al.: Learning to communicate implicitly by actions (2019)"},{"key":"21_CR23","unstructured":"Wen, Y., Yang, Y., Luo, R., Wang, J., Pan, W.: Probabilistic recursive reasoning for multi-agent reinforcement learning (2019)"},{"key":"21_CR24","unstructured":"Wiyatno, R., Xu, A.: Maximal Jacobian-based saliency map attack (2018)"},{"key":"21_CR25","unstructured":"Wu, X., Guo, W., Wei, H., Xing, X.: Adversarial policy training against deep reinforcement learning. In: 30th USENIX Security Symposium (USENIX Security 21), pp. 1883\u20131900. USENIX Association (2021). https:\/\/www.usenix.org\/conference\/usenixsecurity21\/presentation\/wu-xian"},{"key":"21_CR26","unstructured":"Xia, Y., Qin, T., Chen, W., Bian, J., Yu, N., Liu, T.Y.: Dual supervised learning (2017)"},{"key":"21_CR27","unstructured":"Yang, Y., Luo, R., Li, M., Zhou, M., Zhang, W., Wang, J.: Mean field multi-agent reinforcement learning (2018)"},{"key":"21_CR28","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Shumailov, I., Cui, H., Gao, X., Mullins, R., Anderson, R.: Blackbox attacks on reinforcement learning agents using approximated temporal information (2019)","DOI":"10.1109\/DSN-W50199.2020.00013"}],"container-title":["Lecture Notes in Computer Science","PRIMA 2022: Principles and Practice of Multi-Agent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-21203-1_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,11]],"date-time":"2022-11-11T07:38:27Z","timestamp":1668152307000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-21203-1_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,12]]},"ISBN":["9783031212024","9783031212031"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-21203-1_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022,11,12]]},"assertion":[{"value":"12 November 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRIMA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Principles and Practice of Multi-Agent Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Valencia","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 November 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 November 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"prima2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/prima2022.webs.upv.es\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"100","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"31","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"15","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"31% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1 (demo paper)","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}