{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T23:28:24Z","timestamp":1774913304395,"version":"3.50.1"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T00:00:00Z","timestamp":1732060800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T00:00:00Z","timestamp":1732060800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Discov Internet Things"],"DOI":"10.1007\/s43926-024-00080-7","type":"journal-article","created":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T19:51:30Z","timestamp":1732132290000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Adaptive epsilon greedy reinforcement learning method in securing IoT devices in edge computing"],"prefix":"10.1007","volume":"4","author":[{"given":"Anit","family":"Kumar","sequence":"first","affiliation":[]},{"given":"Dhanpratap","family":"Singh","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,20]]},"reference":[{"issue":"4","key":"80_CR1","doi-asserted-by":"publisher","first-page":"628","DOI":"10.3390\/network2040036","volume":"2","author":"G Fox","year":"2022","unstructured":"Fox G, Boppana RV. Detection of malicious network flows with low preprocessing overhead. Network. 2022;2(4):628\u201342.","journal-title":"Network"},{"key":"80_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2022\/5061059","volume":"2022","author":"N Albishry","year":"2022","unstructured":"Albishry N, AlGhamdi R, Almalawi A, Khan AI, Kshirsagar PR. An attribute extraction for automated malware attack classification and detection using soft computing techniques. Comput Intell Neurosci. 2022;2022:1\u201313.","journal-title":"Comput Intell Neurosci"},{"key":"80_CR3","doi-asserted-by":"crossref","unstructured":"Kumar A, Chawla P. A systematic literature review on load balancing algorithms of virtual machines in a Cloud computing environment. In: Proceedings of the International Conference on Innovative Computing & Communications (ICICC). 2020.","DOI":"10.2139\/ssrn.3564355"},{"key":"80_CR4","doi-asserted-by":"crossref","unstructured":"Kumar A, Singh D. Artificial intelligent load balance agent on network traffic across multiple heterogeneous distributed computing systems. 2020.","DOI":"10.2139\/ssrn.3739322"},{"key":"80_CR5","doi-asserted-by":"crossref","unstructured":"Kumar A. Detection and prevention of DDoS attacks on edge computing of IoT devices through reinforcement learning. Int J Inf Technol. 2023; 1\u201312.","DOI":"10.1007\/s41870-023-01704-x"},{"key":"80_CR6","doi-asserted-by":"publisher","first-page":"012016","DOI":"10.1088\/1742-6596\/2327\/1\/012016","volume":"2327","author":"A Kumar","year":"2022","unstructured":"Kumar A, Singh D. Detection of security attacks on edge computing of IoT devices through NS2 simulation. J Phys Conf Ser. 2022;2327:012016.","journal-title":"J Phys Conf Ser"},{"key":"80_CR7","doi-asserted-by":"crossref","unstructured":"Kumar A. A Comprehensive survey on security attacks to edge server of IoT devices through reinforcement learning. In: Proceedings of the AICTE sponsored National conference on Multidisciplinary Research and Innovation-21 (NCMRAI-21). 2022.","DOI":"10.2139\/ssrn.4253769"},{"issue":"4","key":"80_CR8","first-page":"4415","volume":"56","author":"ME Khoda","year":"2019","unstructured":"Khoda ME, Imam T, Kamruzzaman J, Gondal I, Rahman A. Robust malware defense in industrial IoT applications using machine learning with selective adversarial samples. IEEE Trans Ind Appl. 2019;56(4):4415\u201324.","journal-title":"IEEE Trans Ind Appl"},{"key":"80_CR9","unstructured":"Gottipati SK, Pathak Y, Nuttall R, Chunduru R, Touati A, Subramanian SG, Taylor ME, Chandar S. Maximum reward formulation in reinforcement learning. arXiv preprint arXiv:2010.03744; 2020."},{"key":"80_CR10","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1007\/s11235-017-0340-1","volume":"67","author":"X Li","year":"2018","unstructured":"Li X, Ibrahim MH, Kumari S, Kumar R. Secure and efficient anonymous authentication scheme for three-tier mobile healthcare systems with wearable sensors. Telecommun Syst. 2018;67:323\u201348.","journal-title":"Telecommun Syst"},{"issue":"6","key":"80_CR11","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1109\/MCE.2018.2851723","volume":"7","author":"F Lin","year":"2018","unstructured":"Lin F, Zhou Y, An X, You I, Choo K-KR. Fair resource allocation in an intrusion-detection system for edge computing: ensuring the security of Internet of Things devices. IEEE Consumer Electron Magaz. 2018;7(6):45\u201350.","journal-title":"IEEE Consumer Electron Magaz"},{"key":"80_CR12","doi-asserted-by":"publisher","first-page":"23626","DOI":"10.1109\/ACCESS.2018.2831898","volume":"6","author":"J Yuan","year":"2018","unstructured":"Yuan J, Li X. A reliable and lightweight trust computing mechanism for IoT edge devices based on multi-source feedback information fusion. IEEE Access. 2018;6:23626\u201338.","journal-title":"IEEE Access"},{"key":"80_CR13","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1016\/j.comnet.2019.04.031","volume":"159","author":"A Arfaoui","year":"2019","unstructured":"Arfaoui A, Kribeche A, Senouci S-M. Context-aware anonymous authentication protocols in the internet of things dedicated to e-health applications. Comput Netw. 2019;159:23\u201336.","journal-title":"Comput Netw"},{"issue":"23","key":"80_CR14","doi-asserted-by":"publisher","first-page":"5922","DOI":"10.1109\/TSP.2019.2949504","volume":"67","author":"B Li","year":"2019","unstructured":"Li B, Chen T, Giannakis GB. Secure mobile edge computing in IoT via collaborative online learning. IEEE Trans Signal Process. 2019;67(23):5922\u201335.","journal-title":"IEEE Trans Signal Process"},{"key":"80_CR15","doi-asserted-by":"crossref","unstructured":"Chaudhary P, Gupta BB. DDos detection framework in resource constrained internet of things domain. In: 2019 IEEE 8th Global Conference on Consumer Electronics (GCCE). IEEE, 2019.","DOI":"10.1109\/GCCE46687.2019.9015465"},{"key":"80_CR16","doi-asserted-by":"publisher","first-page":"1146","DOI":"10.1016\/j.procs.2017.05.431","volume":"109","author":"A dos Santos Mignon","year":"2017","unstructured":"dos Santos Mignon A, Ricardo de Azevedoda Rocha L. An adaptive implementation of \u03b5-greedy in reinforcement learning. Proc Comput Sci. 2017;109:1146\u201351.","journal-title":"Proc Comput Sci"},{"key":"80_CR17","unstructured":"Epsilon-Greedy Algorithm in Reinforcement Learning\u2014GeeksforGeeks. Accessed 21 Mar 2024,"},{"key":"80_CR18","doi-asserted-by":"publisher","DOI":"10.1007\/s41870-023-01508-z","author":"A Kumar","year":"2023","unstructured":"Kumar A. Detection and prevention of DDoS attacks on edge computing of IoT devices through reinforcement learning. Int J Inf Technol. 2023. https:\/\/doi.org\/10.1007\/s41870-023-01508-z.","journal-title":"Int J Inf Technol"},{"issue":"5","key":"80_CR19","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1109\/MNET.2018.1700284","volume":"32","author":"R-H Hsu","year":"2018","unstructured":"Hsu R-H, Lee J, Quek TQS, Chen J-C. Reconfigurable security: edge-computing-based framework for IoT. IEEE Netw. 2018;32(5):92\u20139.","journal-title":"IEEE Netw"},{"key":"80_CR20","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192","volume-title":"Introduction to reinforcement learning","author":"RS Sutton","year":"1998","unstructured":"Sutton RS, Barto AG. Introduction to reinforcement learning. Cambridge: MIT Press; 1998."},{"key":"80_CR21","doi-asserted-by":"crossref","unstructured":"Kumar A, Singh D. Resource-aware dynamic load balancing system in heterogeneous distributed computing systems through swarm intelligence. 2020.","DOI":"10.2139\/ssrn.3734997"},{"key":"80_CR22","unstructured":"ESP-WROOM-32 Tutorial: Uploading a program with Arduino IDE\u2014EverythingESP. Accessed on 24 Mar 2024."},{"key":"80_CR23","doi-asserted-by":"publisher","first-page":"8996","DOI":"10.1109\/JIOT.2022.3232587","volume":"10","author":"T Zhang","year":"2023","unstructured":"Zhang T, Wen H, Jiang Y, Tang J. Deep reinforcement learning based IRS for cooperative jamming networks under edge computing. IEEE Internet Things J. 2023;10:8996.","journal-title":"IEEE Internet Things J"},{"issue":"4","key":"80_CR24","doi-asserted-by":"publisher","first-page":"2410","DOI":"10.1109\/TNSM.2020.3020249","volume":"17","author":"IA Elgendy","year":"2020","unstructured":"Elgendy IA, Zhang W-Z, Zeng Y, He H, Tian Y-C, Yang Y. Efficient and secure multi-user multi-task computation offloading for mobile-edge computing in mobile IoT networks. IEEE Trans Netw Serv Manage. 2020;17(4):2410\u201322.","journal-title":"IEEE Trans Netw Serv Manage"},{"key":"80_CR25","doi-asserted-by":"publisher","first-page":"270","DOI":"10.1016\/j.engappai.2015.01.013","volume":"41","author":"K Malialis","year":"2015","unstructured":"Malialis K, Kudenko D. Distributed response to network intrusions using multiagent reinforcement learning. Eng Appl Artif Intell. 2015;41:270\u201384.","journal-title":"Eng Appl Artif Intell"},{"issue":"12","key":"80_CR26","doi-asserted-by":"publisher","first-page":"10037","DOI":"10.1109\/TVT.2016.2524258","volume":"65","author":"L Xiao","year":"2016","unstructured":"Xiao L, Li Y, Han G, Liu G, Zhuang W. PHY-layer spoofing detection with reinforcement learning in wireless networks. IEEE Trans Veh Technol. 2016;65(12):10037\u201347.","journal-title":"IEEE Trans Veh Technol"},{"issue":"22","key":"80_CR27","doi-asserted-by":"publisher","first-page":"4443","DOI":"10.1109\/TITS.2020.3003211","volume":"2021","author":"F Qiao","year":"2020","unstructured":"Qiao F, Wu J, Li J, Bashir AK, Mumtaz S, Tariq U. Trustworthy edge storage orchestration in intelligent transportation systems using reinforcement learning. IEEE Trans Intell Transport Syst. 2020;2021(22):4443. https:\/\/doi.org\/10.1109\/TITS.2020.3003211.","journal-title":"IEEE Trans Intell Transport Syst."},{"key":"80_CR28","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1016\/j.arcontrol.2022.01.001","volume":"53","author":"Y Huang","year":"2022","unstructured":"Huang Y, Huang L, Zhu Q. Reinforcement learning for feedback-enabled cyber resilience. Annu Rev Control. 2022;53:273\u201395.","journal-title":"Annu Rev Control"},{"key":"80_CR29","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2017.08.043","author":"AA Diro","year":"2017","unstructured":"Diro AA, Chilamkurti N. Distributed attack detection scheme using deep learning approach for internet of things. Future Gen Comput Syst. 2017. https:\/\/doi.org\/10.1016\/j.future.2017.08.043.","journal-title":"Future Gen Comput Syst"},{"key":"80_CR30","doi-asserted-by":"crossref","unstructured":"https:\/\/builtin.com\/machine-learning\/markov-decision-process. Accessed 23 Jul 2024.","DOI":"10.1007\/978-981-19-4933-3_2"},{"key":"80_CR31","unstructured":"https:\/\/www.wireshark.org\/. Accessed 23 Mar 2024."},{"key":"80_CR32","unstructured":"https:\/\/www.espressif.com\/en\/products\/socs\/esp32. Accessed 22 Mar 2024."},{"key":"80_CR33","unstructured":"https:\/\/en.wikipedia.org\/wiki\/ESP32. Accessed 22 Mar 2024."},{"key":"80_CR34","unstructured":"https:\/\/mcfp.felk.cvut.cz\/publicDatasets\/IoT-23-Dataset\/IndividualScenarios\/CTU-IoT-Malware-Capture-34-1\/. Accessed on 22 Mar 2024."},{"key":"80_CR35","unstructured":"https:\/\/www.isi.edu\/nsnam\/ns\/tutorial\/. Accessed 22 Mar 2024."},{"key":"80_CR36","unstructured":"https:\/\/www.nsnam.com\/2020\/06\/installation-of-ns2-ns-235-in-ubuntu.html. Accessed 22 Mar 2024."},{"key":"80_CR37","unstructured":"https:\/\/medium.com\/nerd-for-tech\/aodv-routing-protocol-network-simulation-53f3a23918aa. Accessed on 28 May 2022."},{"key":"80_CR38","unstructured":"https:\/\/mosquitto.org\/. Accessed on 22 Mar 2024."},{"key":"80_CR39","unstructured":"https:\/\/cookbook.nodered.org\/mqtt\/connect-to-broker. Accessed 22 Mar 2024."},{"key":"80_CR40","unstructured":"An introduction to Q-learning: a tutorial for beginners|DataCamp. Accessed on 11 Apr 2024."},{"key":"80_CR41","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1023\/A:1022676722315","volume":"8","author":"CJ Watkins","year":"1992","unstructured":"Watkins CJ, Dayan P. Technical note: Q-learning. Mach Learn. 1992;8:279\u201392. https:\/\/doi.org\/10.1023\/A:1022676722315.","journal-title":"Mach Learn"},{"key":"80_CR42","unstructured":"https:\/\/www.freecodecamp.org\/news\/an-introduction-to-q-learning-reinforcement-learning-14ac0b4493cc\/. Accessed 13 Apr 2024."},{"key":"80_CR43","unstructured":"Checksum in Networking|Checksum Example|Gate Vidyalay. Accessed 23 Mar 2024."},{"key":"80_CR44","unstructured":"Implementing Checksum Using Java \u2013 GeeksforGeeks. Accessed 23 Mar 2024."},{"key":"80_CR45","unstructured":"Christiana I, Vassiliou V. Classifying security attacks in IoT networks using supervised learning. In: 2019 15th International conference on distributed computing in sensor systems (DCOSS). IEEE, 2019."},{"key":"80_CR46","doi-asserted-by":"crossref","unstructured":"Khatun MA, Chowdhury N, Uddin MN. Malicious nodes detection based on artificial neural network in iot environments. In: 2019 22nd International Conference on Computer and Information Technology (ICCIT). IEEE, 2019.","DOI":"10.1109\/ICCIT48885.2019.9038563"},{"key":"80_CR47","doi-asserted-by":"publisher","first-page":"78482","DOI":"10.1109\/ACCESS.2020.2989353","volume":"8","author":"H Zhang","year":"2020","unstructured":"Zhang H, Hao J, Li X. A method for deploying distributed denial of service attack defense strategies on edge servers using reinforcement learning. IEEE Access. 2020;8:78482\u201391.","journal-title":"IEEE Access"},{"key":"80_CR48","doi-asserted-by":"crossref","unstructured":"Bhunia S, Sengupta S, V\u00e1zquez-Abad F. Cr-honeynet: a learning & decoy based sustenance mechanism against jamming attack in crn. In: 2014 IEEE Military Communications Conference, pp. 1173\u20131180. IEEE, 2014.","DOI":"10.1109\/MILCOM.2014.197"},{"key":"80_CR49","doi-asserted-by":"crossref","unstructured":"Mishra, Kamta Nath, Vandana Bhattacharjee, Shashwat Saket, and Shivam Prakash Mishra. \"Security provisions in smart edge computing devices using blockchain and machine learning algorithms: a novel approach.\" Cluster Computing (2022): 1\u201326.","DOI":"10.21203\/rs.3.rs-1714576\/v1"}],"container-title":["Discover Internet of Things"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s43926-024-00080-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s43926-024-00080-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s43926-024-00080-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T20:05:23Z","timestamp":1732133123000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s43926-024-00080-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,20]]},"references-count":49,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["80"],"URL":"https:\/\/doi.org\/10.1007\/s43926-024-00080-7","relation":{},"ISSN":["2730-7239"],"issn-type":[{"value":"2730-7239","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,20]]},"assertion":[{"value":"8 June 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 November 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 November 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The manuscript in part or in full has not been submitted or published anywhere else.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"The authors declare no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"27"}}