{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T16:56:10Z","timestamp":1776444970368,"version":"3.51.2"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T00:00:00Z","timestamp":1590969600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T00:00:00Z","timestamp":1590969600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T00:00:00Z","timestamp":1590969600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,6]]},"DOI":"10.1109\/netsoft48620.2020.9165383","type":"proceedings-article","created":{"date-parts":[[2020,8,12]],"date-time":"2020-08-12T21:29:37Z","timestamp":1597267777000},"page":"282-286","source":"Crossref","is-referenced-by-count":36,"title":["Reinforcement Learning for Attack Mitigation in SDN-enabled Networks"],"prefix":"10.1109","author":[{"given":"Mikhail","family":"Zolotukhin","sequence":"first","affiliation":[]},{"given":"Sanjay","family":"Kumar","sequence":"additional","affiliation":[]},{"given":"Timo","family":"Hamalainen","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2017.23200"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2803446"},{"key":"ref12","first-page":"533","article-title":"Enforcing network-wide policies in the presence of dynamic middlebox actions using FlowTags","author":"fayazbakhsh","year":"2014","journal-title":"Proc of NSDI"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2013.8"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2016.2615622"},{"key":"ref15","first-page":"633","author":"zolotukhin","year":"2012","journal-title":"Growing Hierarchical Self-organising Maps for Online Anomaly Detection by using Network Logs Proc of WEBIST"},{"key":"ref16","first-page":"1093","author":"antonakakis","year":"2017","journal-title":"Understanding the mirai botnet Proc of the 26th USENIX Conference on Security Symposium (SEC)"},{"key":"ref17","author":"brockman","year":"2016","journal-title":"OpenAI Gym"},{"key":"ref18","author":"dhariwal","year":"2017","journal-title":"OpenAI Baselines GitHub"},{"key":"ref19","author":"mnih","year":"2013","journal-title":"Playing atari with deep reinforcement learning"},{"key":"ref4","author":"popov","year":"2018","journal-title":"Data-efficient Deep Reinforcement Learning for Dexterous Manipulation"},{"key":"ref3","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11796","article-title":"Rainbow: Combining improvements in deep reinforcement learning","author":"hessel","year":"2018","journal-title":"Proc Of AAAI"},{"key":"ref6","first-page":"49","article-title":"Adaptive intrusion detection based on machine learning: feature extraction, classifier construction and sequential pattern prediction","volume":"2","author":"xu","year":"2006","journal-title":"International Journal of Web Services Practices"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SCC.2016.12"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2908033"},{"key":"ref7","first-page":"211","article-title":"Multi-agent reinforcement learning for intrusion detection","author":"kudenko","year":"2008","journal-title":"Adaptive Agents and Multi-Agent Systems III Adaptation and Multi-Agent Learning"},{"key":"ref2","article-title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","author":"haarnoja","year":"2018","journal-title":"Proc of ICML"},{"key":"ref9","article-title":"Iot candy jar: Towards an intelligent-interaction honeypot for iot devices","author":"luo","year":"2017","journal-title":"Black Hat"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CNS.2018.8433203"},{"key":"ref20","author":"schulman","year":"2017","journal-title":"Proximal policy optimization algorithms"}],"event":{"name":"2020 6th IEEE International Conference on Network Softwarization (NetSoft)","location":"Ghent, Belgium","start":{"date-parts":[[2020,6,29]]},"end":{"date-parts":[[2020,7,3]]}},"container-title":["2020 6th IEEE Conference on Network Softwarization (NetSoft)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9158198\/9165305\/09165383.pdf?arnumber=9165383","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,6]],"date-time":"2022-11-06T19:12:40Z","timestamp":1667761960000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9165383\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/netsoft48620.2020.9165383","relation":{},"subject":[],"published":{"date-parts":[[2020,6]]}}}