Cyber security threat detection model using artificial intelligence technology

O. Ramyateja; Padilam Navya Sahithi; Samanthula Vaishnavi; Perolla Shirisha

Author(s)

O. Ramyateja Department of Information Technology Malla Reddy Engineering College for Women (UGC – Autonomous), Maisammaguda, Hyderabad, 500100, Telangana.India

Padilam Navya Sahithi Department of Information Technology Malla Reddy Engineering College for Women (UGC – Autonomous), Maisammaguda, Hyderabad, 500100, Telangana.India

Samanthula Vaishnavi Department of Information Technology Malla Reddy Engineering College for Women (UGC – Autonomous), Maisammaguda, Hyderabad, 500100, Telangana.India

Perolla Shirisha Department of Information Technology Malla Reddy Engineering College for Women (UGC – Autonomous), Maisammaguda, Hyderabad, 500100, Telangana.India

Abstract

Botnets-networks of compromised computers controlled by malicious actors-continue to pose a major threat to cybersecurity. Their impact is amplified by the use of Domain Generation Algorithms (DGAs), which dynamically produce new domain names for command-and-control servers, making traditional signature- and rule-based detection methods increasingly ineffective. This challenge underscores the need to enhance botnet DGA detection, particularly as attackers refine their techniques to outmaneuver existing defenses. In this work, we propose an approach that integrates Explainable AI (XAI) with open-source intelligence (OSINT) to improve the detection and understanding of botnet DGAs. Explainable AI provides visibility into the decision-making processes of detection models, fostering greater trust and insight into why certain activities are flagged as malicious. Meanwhile, open-source intelligence enables collaborative threat information sharing, which is essential for a collective defense strategy. By combining advanced analytic capabilities with real-time intelligence exchange, this integrated framework aims to stay ahead of rapidly evolving cyber threats, ultimately enhancing both the accuracy and transparency of botnet DGA detection.

Publication Details

Page(s) 610-619

DOI DOI not available

Published Journal: International Journal of Communication Networks and Information Security, Volume: 16, Issue: 05, Year: 2024

Request the full text from PASTIC

Keywords

Botnets, Domain Generation Algorithms, Cyber Threat Intelligence, Open-Source Intelligence, Explainable AI

References

Suryotrisongko H.,Tsuneda Y.,Sugitani A.,K. A. .2022 .Robust botnet DGA detection: Blending XAI and OSINT for CTI sharing. IEEE Access, 10 : 34613-34624.

Moraliyage H.,Sumanasena H.,De Silva D.,R. D.,Alahakoon L.,D. L. .2022 .Multimodal classification of onion services for proactive CTI using explainable deep learning. IEEE Access, 10 : 56044-56056.

Irshad E.,Siddiqui A.B. .2023 .Cyber threat attribution using unstructured reports in CTI. , 24 : 43-59.

Zhang G.,Cui C.,Jiang Y.,C. Y. .2021 .Ex-action: Automatically extracting threat actions from CTI report based on multimodal learning. Secur. Commun. Netw, : 1-12.

Cha J.,Singh S.K.,Pan Y.,Park J.H. .2020 .Blockchain-based CTI system architecture for sustainable computing. Sustainability, 12 : 6401.

Gong S.,Lee C. .2021 .CTI framework for incident response in an energy cloud platform. Electronics, 10 : 239.

Ejaz S.,Rashid U.,Z. U. .2022 .Visualizing Interesting Patterns in CTI Using Machine Learning Techniques. Cybern. Inf. Technol, 22 : 96-113.

Mena Mendez,Yang D.,B. D. .2020 .Decentralized actionable CTI for networks and the internet of things. IoT, 2 : 1-16.

Liu J.,Yan J.,Jiang J.,Wang Y.,Jiang X.,Yang Z.,Li P.,N. P. .2022 .TriCTI: An actionable CTI discovery system via trigger-enhanced neural network. Cybersecurity, 5 : 8.

Kiwia D.,Dehghantanha A.,Choo A.,K.K.R.; Slaughter J. .2018 .A cyber kill chain based taxonomy of banking Trojans for evolutionary computational intelligence. J. Comput. Sci, 27 : 394-409.