{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T19:39:53Z","timestamp":1785267593610,"version":"3.55.0"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"National Key Research Development Program of China","award":["2017YFB0802800"],"award-info":[{"award-number":["2017YFB0802800"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2019]]},"DOI":"10.1109\/access.2019.2923993","type":"journal-article","created":{"date-parts":[[2019,6,20]],"date-time":"2019-06-20T21:28:42Z","timestamp":1561066122000},"page":"81481-81493","source":"Crossref","is-referenced-by-count":8,"title":["DDoS Traffic Control Using Transfer Learning DQN With Structure Information"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8162-9091","authenticated-orcid":false,"given":"Shi-Ming","family":"Xia","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Bai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xing-Yu","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhi-Song","family":"Pan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1007\/978-3-540-87805-6_15","article-title":"Multi-agent reinforcement learning for intrusion detection: A case study and evaluation","author":"servin","year":"2008","journal-title":"Proc 8th German Conf Multiagent Syst Technol"},{"key":"ref38","first-page":"229","article-title":"Snort: Lightweight intrusion detection for networks","volume":"99","author":"roesch","year":"1999","journal-title":"LISA"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref32","article-title":"Experience replay for continual learning","author":"rolnick","year":"2018","journal-title":"arXiv 1811 11682"},{"key":"ref31","article-title":"Fully decentralized multi-agent reinforcement learning with networked agents","author":"zhang","year":"2018","journal-title":"arXiv 1802 08757"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.17487\/rfc2827"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2017.2664665"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/BRACIS.2016.027"},{"key":"ref34","first-page":"270","article-title":"A survey on deep transfer learning","author":"tan","year":"2018","journal-title":"Proc Int Conf Artif Neural Netw"},{"key":"ref28","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1994.6.2.215"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/375735.376302"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICNP.2002.1181418"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2017.62"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/997150.997156"},{"key":"ref22","first-page":"1799","article-title":"Deep learning: Yesterday, today, and tomorrow","volume":"50","author":"yu","year":"2013","journal-title":"J Comput Res Develop"},{"key":"ref21","first-page":"1146","article-title":"Stabilising experience replay for deep multi-agent reinforcement learning","volume":"70","author":"foerster","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.09.003"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"bengio","year":"2015","journal-title":"Nature"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1145\/1394608.1382172","article-title":"Self-optimizing memory controllers: A reinforcement learning approach","volume":"36","author":"ipek","year":"2008","journal-title":"ACM SIGARCH Comput Archit News"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"10026","DOI":"10.3390\/s150510026","article-title":"A multi-agent framework for packet routing in wireless sensor networks","volume":"15","author":"ye","year":"2015","journal-title":"SENSORS"},{"key":"ref50","first-page":"1633","article-title":"Transfer learning for reinforcement learning domains: A survey","volume":"10","author":"taylor","year":"2009","journal-title":"J Mach Learn Res"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-16138-4_16"},{"key":"ref11","first-page":"95","article-title":"Adaptive tile coding for value function approximation","volume":"5","author":"whiteson","year":"2007","journal-title":"Biogeosciences"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-71549-8_17"},{"key":"ref12","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"arXiv 1312 5602"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref14","first-page":"187a","article-title":"Continuous control with deep reinforcement learning","volume":"8","author":"lillicrap","year":"2015","journal-title":"Comput Sci"},{"key":"ref15","article-title":"Parameter sharing deep deterministic policy gradient for cooperative multi-agent reinforcement learning","author":"chu","year":"2017","journal-title":"arXiv 1710 00336"},{"key":"ref16","article-title":"Improving coordination in multi-agent deep reinforcement learning through memory-driven communication","author":"pesce","year":"2019","journal-title":"arXiv 1901 03887"},{"key":"ref17","first-page":"2137","article-title":"Learning to communicate with deep multi-agent reinforcement learning","author":"foerster","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2003.10.003"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2017.201"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2846040"},{"key":"ref6","first-page":"1551","article-title":"Multiagent router throttling: Decentralized coordinated response against DDoS attacks","author":"malialis","year":"2013","journal-title":"Proc 25th IAAI Conf"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-45871-7_12"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2004.842221"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2015.01.013"},{"key":"ref49","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref9","first-page":"30","article-title":"Residual algorithms: Reinforcement learning with function approximation","author":"baird","year":"1995","journal-title":"Proc 12th Int Conf Mach Learn"},{"key":"ref46","first-page":"1233","article-title":"MF (minority first) scheme for defeating distributed denial of service attacks","author":"ahn","year":"2003","journal-title":"Proc 8th IEEE Symp Comput Commun (ISCC)"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/2185376.2185386"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-59072-1_6"},{"key":"ref47","first-page":"490","article-title":"On the existence of fixed points for Q-learning and Sarsa in partially observable domains","author":"perkins","year":"2002","journal-title":"Proc ICML"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/964725.633032"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/347057.347560"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/DISCEX.2003.1194868"},{"key":"ref43","article-title":"DDoS attack and interception resistance IP fast hopping based protocol","author":"krylov","year":"2014","journal-title":"arXiv 1403 7371"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8600701\/08742593.pdf?arnumber=8742593","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T14:53:38Z","timestamp":1643295218000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8742593\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/access.2019.2923993","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]}}}