Dueling Deep Q-Learning for Intrusion Detection

Computer Science > Cryptography and Security [Submitted on 11 Aug 2026] Dueling Deep Q-Learning for Intrusion Detection Logan Luna (Georgia Institute of Technology), Matthew P. Berkowitz (Embry-Riddle Aeronautical University), Laxima Niure Kandel (Embry-Riddle Aeronautical University), Sirio Jansen-S'anchez (Embry-Riddle Aeronautical University) Intrusion detection systems (IDS) and automated systems for detecting and reporting cyber threats, are commonly handled via supervised machine learning methods. Though effective, these models struggle to effectively adapt to new attack types. This study proposes a novel approach by employing a reward-based, dueling Q-learning model for IDS, achieving an average accuracy of 99.68% across multiple attack classes. The proposed model has a dueling network architecture which separates its predictions into value and advantage streams. This has the benefit of improving learning efficiency and stability. The model was trained on the CIC-IDS2018, a benchmark dataset based on real-world intrusion detection scenarios, having multiple attack classes such as DDoS, botnets, and brute-force attacks. Furthermore, Explainable AI (XAI), specifically SHAP (SHapley Additive exPlanations), was also integrated into the training and evaluation process to provide interpretability into the model's predictions. Comments: 6 pages, 5 figures. Published in Proc. IEEE SoutheastCon 2025, pp. 1192-1197 Subjects: Cryptography and Security (cs.CR); Machine Learning (cs.LG) ACM classes: I.2.6; K.6.5 Cite as: arXiv:2608.11291 [cs.CR]   (or arXiv:2608.11291v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2608.11291 Focus to learn more Journal reference: L. Luna, M. P. Berkowitz, L. Niure Kandel, and S. Jansen-Sánchez, "Dueling Deep Q-Learning for Intrusion Detection," in Proc. IEEE SoutheastCon 2025, pp. 1192-1197, 2025 Related DOI: https://doi.org/10.1109/SOUTHEASTCON56624.2025.10971436 Focus to learn more Submission history From: Logan Luna [view email] [v1] Tue, 11 Aug 2026 16:55:00 UTC (429 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-08 Change to browse by: cs cs.LG References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)