2026-05-30T19:59:02.083Z http://ezaposleni.singidunum.ac.rs/rest/sciNaucniRezultati/oai

ezaposleni.singidunum.ac.rs/rest/sciNaucniRezultati/oai:3:9278 2023-02-28T12:16:36Z 3

Intrusion Detection by XGBoost Model Tuned by Improved Social Network Search Algorithm, Chapter in CCIS Communications in Computer and Information Science: MDIS 2022: Modelling and Development of Intelligent Systems, Springer, volume 1761 2023 http://ezaposleni.singidunum.ac.rs/rest/sciNaucniRezultati/oai/record/3/9278 https://link.springer.com/chapter/10.1007/978-3-031-27034-5_7 N. Bacanin A. Petrovic M. Antonijevic M. Zivkovic M. Sarac E. Tuba I. Strumberger The industry 4.0 flourished recently due to the advances in a number of contemporary fields, alike artificial intelligence and internet of things. It significantly improved the industrial process and factory production, by relying on the communication between devices, production machines and equipment. The biggest concern in this process is security, as each of the network-connected components is vulnerable to the malicious attacks. Intrusion detection is therefore a key aspect and the largest challenge in the industry 4.0 domain. To address this issue, a novel framework, based on the XGBoost machine learning model, tuned with a modified variant of social network search algorithm, is proposed. The introduced framework and algorithm have been evaluated on a challenging UNSW-NB 15 benchmark intrusion detection dataset, and the experimental findings were put into comparison against the outcomes of other high performing metaheuristics for the same problem. For comparison purposes, alongside the original version of social network search, harris hawk optimization algorithm, firefly algorithm, bat algorithm, and artificial bee colony, were also adopted for XGBoost tuning and validated against the same internet of things security benchmark dataset. Experimental findings proved that the best performing developed XGBoost model is the one which is tuned by introduced modified social network search algorithm, outscoring others in most of performance indicators which were employed for evaluation purposes. bookPart Springer, Cham 104 121 10.1007/978-3-031-27034-5_7 CCIS Communications in Computer and Information Science: MDIS 2022: Modelling and Development of Intelligent Systems, volume 1761