OB-IDS: Optimized BERT-Based Intrusion Detection System

dc.contributor.author Ates, G.
dc.contributor.author Celebi, B.
dc.contributor.author Semerci, U.A.
dc.contributor.author Capkan, E.
dc.contributor.author Yildirim, B.
dc.contributor.author Ar, I.
dc.contributor.author Arsan, T.
dc.date.accessioned 2025-12-15T15:38:31Z
dc.date.available 2025-12-15T15:38:31Z
dc.date.issued 2025
dc.description.abstract "OB-IDS (Optimized BERT-based Intrusion Detection System)"presents a lightweight IDS optimized for the resource-constrained environments. The proposed system which employs quantization, pruning, knowledge distillation and self distillation methods is developed in a multi-stage optimization manner. It was evaluated on UNSW-NB15 and CIC-IDS2017 datasets. The proposed system was found to significantly reduce the inference time and memory usage while maintaining high classification accuracy. The experimental results demonstrate the applicability of Transformer-based IDSs for real-time threat detection in resource-constrained environments. © 2025 IEEE. en_US
dc.identifier.doi 10.1109/BlackSeaCom65655.2025.11193891
dc.identifier.isbn 9798331537197
dc.identifier.scopus 2-s2.0-105021003093
dc.identifier.uri https://doi.org/10.1109/BlackSeaCom65655.2025.11193891
dc.identifier.uri https://hdl.handle.net/20.500.12469/7663
dc.language.iso en en_US
dc.publisher Institute of Electrical and Electronics Engineers Inc. en_US
dc.relation.ispartof -- 2025 IEEE International Black Sea Conference on Communications and Networking, BlackSeaCom 2025 -- 2025-06-23 through 2025-06-26 -- Chisinau -- 213945 en_US
dc.rights info:eu-repo/semantics/closedAccess en_US
dc.subject Bert en_US
dc.subject Cybersecurity en_US
dc.subject Fine-Tuning en_US
dc.subject Intrusion Detection en_US
dc.subject Machine Learning en_US
dc.subject Model Optimization en_US
dc.subject Network Security en_US
dc.subject Quantization en_US
dc.title OB-IDS: Optimized BERT-Based Intrusion Detection System en_US
dc.type Conference Object en_US
dspace.entity.type Publication
gdc.author.institutional Arsan, Taner
gdc.author.scopusid 60170002000
gdc.author.scopusid 60169180500
gdc.author.scopusid 60169180600
gdc.author.scopusid 60169180700
gdc.author.scopusid 57214152308
gdc.author.scopusid 23395861100
gdc.author.scopusid 23395861100
gdc.description.department Kadir Has University en_US
gdc.description.departmenttemp [Ates] Goktug, Department of Computer Engineering, Kadir Has Üniversitesi, Istanbul, Turkey; [Celebi] Basar, Department of Computer Engineering, Kadir Has Üniversitesi, Istanbul, Turkey; [Semerci] Umut Aytug, Department of Computer Engineering, Kadir Has Üniversitesi, Istanbul, Turkey; [Capkan] Emircan, Department of Computer Engineering, Kadir Has Üniversitesi, Istanbul, Turkey; [Yildirim] Batuhan, Department of Computer Engineering, Kadir Has Üniversitesi, Istanbul, Turkey; [Ar] Ilktan, Department of Computer Engineering, Kadir Has Üniversitesi, Istanbul, Turkey; [Arsan] Taner, Department of Computer Engineering, Kadir Has Üniversitesi, Istanbul, Turkey en_US
gdc.description.publicationcategory Konferans Öğesi - Uluslararası - Kurum Öğretim Elemanı en_US
gdc.description.wosquality N/A
relation.isAuthorOfPublication 7959ea6c-1b30-4fa0-9c40-6311259c0914
relation.isAuthorOfPublication.latestForDiscovery 7959ea6c-1b30-4fa0-9c40-6311259c0914
relation.isOrgUnitOfPublication 2457b9b3-3a3f-4c17-8674-7f874f030d96
relation.isOrgUnitOfPublication b20623fc-1264-4244-9847-a4729ca7508c
relation.isOrgUnitOfPublication fd8e65fe-c3b3-4435-9682-6cccb638779c
relation.isOrgUnitOfPublication.latestForDiscovery 2457b9b3-3a3f-4c17-8674-7f874f030d96

Files