{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T13:05:47Z","timestamp":1761743147572},"publisher-location":"Berlin, Heidelberg","reference-count":26,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540878049"},{"type":"electronic","value":"9783540878056"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1007\/978-3-540-87805-6_15","type":"book-chapter","created":{"date-parts":[[2008,9,18]],"date-time":"2008-09-18T22:31:01Z","timestamp":1221777061000},"page":"159-170","source":"Crossref","is-referenced-by-count":24,"title":["Multi-Agent Reinforcement Learning for Intrusion Detection: A Case Study and Evaluation"],"prefix":"10.1007","author":[{"given":"Arturo","family":"Servin","sequence":"first","affiliation":[]},{"given":"Daniel","family":"Kudenko","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"15_CR1","unstructured":"Awerbuch, B., Holmer, D., Rubens, H.: Provably Secure Competitive Routing against Proactive Byzantine Adversaries via Reinforcement Learning. John Hopkins University, Tech. Rep. (May 2003)"},{"key":"15_CR2","unstructured":"Barford, P., Jha, S., Yegneswaran, V.: Fusion and filtering in distributed intrusion detection systems. In: Proceedings of the 42nd Annual Allerton Conference on Communication, Control and Computing (September 2004)"},{"key":"15_CR3","first-page":"671","volume":"6","author":"J. Boyan","year":"1994","unstructured":"Boyan, J., Littman, M.: Packet routing in dynamically changing networks: A reinforcement learning approach. Advances in Neural Information Processing Systems\u00a06, 671\u2013678 (1994)","journal-title":"Advances in Neural Information Processing Systems"},{"key":"15_CR4","doi-asserted-by":"crossref","unstructured":"Cannady, J.: Applying CMAC-based on-line learning to intrusion detection. In: Proceedings of the International Joint Conference on Neural Networks, vol.\u00a05, pp. 405\u2013410 (2000)","DOI":"10.1109\/IJCNN.2000.861503"},{"key":"15_CR5","unstructured":"Cannady, J.: Next Generation Intrusion Detection: Autonomous Reinforcement Learning of Network Attacks. In: Proc. 23rd National Information Systems Security Conference (2000)"},{"key":"15_CR6","unstructured":"CheckPoint. CheckPoint, N.G.X.: Firewall SmartDefense (June 2008), http:\/\/www.checkpoint.com\/products\/ips-1\/index.html"},{"key":"15_CR7","unstructured":"Cisco. Configuring Anomaly Detections (June 2008), http:\/\/www.cisco.com\/en\/US\/docs\/security\/ips\/6.1\/configuration\/guide\/cli\/cli_anomaly_detection.html"},{"issue":"3","key":"15_CR8","doi-asserted-by":"publisher","first-page":"360","DOI":"10.1109\/TSMCA.2005.846390","volume":"35","author":"J. Dowling","year":"2005","unstructured":"Dowling, J., Curran, E., Cunningham, R., Cahill, V.: Using feedback in collaborative reinforcement learning to adaptively optimize MANET routing. Systems, Man and Cybernetics, Part A, IEEE Transactions on\u00a035(3), 360\u2013372 (2005)","journal-title":"Systems, Man and Cybernetics, Part A, IEEE Transactions on"},{"key":"15_CR9","doi-asserted-by":"crossref","unstructured":"Gelenbe, E., Lent, M., Su, R.: Autonomous smart routing for network QoS. In: Proceedings of International Conference on Autonomic Computing 2004, pp. 232\u2013239 (2004)","DOI":"10.1109\/ICAC.2004.1301368"},{"issue":"2","key":"15_CR10","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1007\/s10458-006-7035-4","volume":"13","author":"M. Ghavamzadeh","year":"2006","unstructured":"Ghavamzadeh, M., Mahadevan, S., Makar, R.: Hierarchical multi-agent reinforcement learning. Autonomous Agents and Multi-Agent Systems\u00a013(2), 197\u2013229 (2006)","journal-title":"Autonomous Agents and Multi-Agent Systems"},{"issue":"2","key":"15_CR11","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1109\/TSMCB.2004.842418","volume":"35","author":"K. Hwang","year":"2005","unstructured":"Hwang, K., Tan, S., Hsiao, M., Wu, C.: Cooperative Multiagent Congestion Control for High-Speed Networks. Systems, Man and Cybernetics, Part B, IEEE Transactions on\u00a035(2), 255\u2013268 (2005)","journal-title":"Systems, Man and Cybernetics, Part B, IEEE Transactions on"},{"key":"15_CR12","unstructured":"Institute, S.: Sans top-20 2007 security risks, 2007 annual update (2008)"},{"key":"15_CR13","unstructured":"Katja Verbeeck1, P.V., Nowe, A.: Networks of learning automata and limiting games. In: Adaptive Learning Agents and Multi Agent Systems 2007, pp. 171\u2013182 (2007)"},{"issue":"3","key":"15_CR14","doi-asserted-by":"publisher","first-page":"216","DOI":"10.1109\/TDSC.2005.35","volume":"2","author":"J. Mirkovic","year":"2005","unstructured":"Mirkovic, J., Reiher, P.: D WARD, A Source-End Defense against Flooding Denial of Service Attacks. Dependable and Secure Computing, IEEE Transactions on\u00a02(3), 216\u2013232 (2005)","journal-title":"Dependable and Secure Computing, IEEE Transactions on"},{"issue":"3","key":"15_CR15","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1007\/s10458-005-2631-2","volume":"11","author":"L. Panait","year":"2005","unstructured":"Panait, L., Luke, S.: Cooperative multi-agent learning: The state of the art. Autonomous Agents and Multi-Agent Systems\u00a011(3), 387\u2013434 (2005)","journal-title":"Autonomous Agents and Multi-Agent Systems"},{"key":"15_CR16","first-page":"1089","volume":"17","author":"R. Powers","year":"2005","unstructured":"Powers, R., Shoham, Y.: New criteria and a new algorithm for learning in multi-agent systems. Advances in Neural Information Processing Systems\u00a017, 1089\u20131096 (2005)","journal-title":"Advances in Neural Information Processing Systems"},{"key":"15_CR17","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/978-3-540-77949-0_15","volume-title":"Adaptive Agents and Multi-Agent Systems III. Adaptation and Multi-Agent Learning","author":"A.L. Servin","year":"2008","unstructured":"Servin, A.L., Kudenko, D.: Multi-agent Reinforcement Learning for Intrusion Detection. In: Tuyls, K., Nowe, A., Guessoum, Z., Kudenko, D. (eds.) ALAMAS 2005, ALAMAS 2006, and ALAMAS 2007. LNCS (LNAI), vol.\u00a04865, pp. 211\u2013223. Springer, Heidelberg (2008)"},{"issue":"7","key":"15_CR18","doi-asserted-by":"publisher","first-page":"365","DOI":"10.1016\/j.artint.2006.02.006","volume":"171","author":"Y. Shoham","year":"2007","unstructured":"Shoham, Y., Powers, R., Grenager, T.: If multi-agent learning is the answer, what is the question? Artificial Intelligence\u00a0171(7), 365\u2013377 (2007)","journal-title":"Artificial Intelligence"},{"key":"15_CR19","doi-asserted-by":"crossref","unstructured":"Siaterlis, C., Maglaris, B.: Towards multisensor data fusion for dos detection. In: Proc. of the 19th ACM Symposium on Applied Computing, Nicosia, Cyprus, pp. 439\u2013446 (2004)","DOI":"10.1145\/967900.967992"},{"key":"15_CR20","unstructured":"N.\u00a0Simulator. 2 (NS2) (January 2008), http:\/\/www.isi.edu\/nsnam\/"},{"key":"15_CR21","unstructured":"I. SourceFire. Snort (June 2008), http:\/\/www.snort.org\/"},{"key":"15_CR22","unstructured":"Sutton, R.: Tile Coding Software, Version 2.0 (2007)"},{"key":"15_CR23","volume-title":"Reinforcement Learning: An Introduction","author":"R. Sutton","year":"1998","unstructured":"Sutton, R., Barto, A.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)"},{"issue":"3","key":"15_CR24","first-page":"279","volume":"8","author":"C. Watkins","year":"1992","unstructured":"Watkins, C., Dayan, P.: Q-learning. Machine Learning\u00a08(3), 279\u2013292 (1992)","journal-title":"Machine Learning"},{"key":"15_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1007\/978-3-540-71549-8_17","volume-title":"Intelligence and Security Informatics","author":"X. Xu","year":"2007","unstructured":"Xu, X., Sun, Y., Huang, Z.: Defending DDoS Attacks Using Hidden Markov Models and Cooperative Reinforcement Learning. In: Yang, C.C., Zeng, D., Chau, M., Chang, K., Yang, Q., Cheng, X., Wang, J., Wang, F.-Y., Chen, H. (eds.) PAISI 2007. LNCS, vol.\u00a04430, p. 196. Springer, Heidelberg (2007)"},{"key":"15_CR26","doi-asserted-by":"crossref","unstructured":"Xu, X., Xie, T.: A Reinforcement Learning Approach for Host-Based Intrusion Detection Using Sequences of System Calls. In: Proceedings of the International Conference on Intelligent Computing (2005)","DOI":"10.1007\/11538059_103"}],"container-title":["Lecture Notes in Computer Science","Multiagent System Technologies"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-87805-6_15.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,23]],"date-time":"2020-11-23T21:06:58Z","timestamp":1606165618000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-87805-6_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"ISBN":["9783540878049","9783540878056"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-87805-6_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[]}}