Dueling Deep Q-Learning for Intrusion Detection

被引:0
作者
Luna, Logan [1 ]
Berkowitz, Matthew P. [1 ]
Kandel, Laxima Niure [1 ]
Jansen-Sanchez, Sirio [1 ]
机构
[1] Embry Riddle Aeronaut Univ, Dept Elect Engn & Comp Sci, Daytona Beach, FL 32114 USA
来源
SOUTHEASTCON 2025 | 2025年
关键词
Intrusion Detection; Reinforcement Learning; Q-Learning; Cybersecurity; Threat Hunting; Explainable AI (XAI); SYSTEMS;
D O I
10.1109/SOUTHEASTCON56624.2025.10971436
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
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.
引用
收藏
页码:1192 / 1197
页数:6
相关论文
共 16 条
[1]   Deep Q-Learning Based Reinforcement Learning Approach for Network Intrusion Detection [J].
Alavizadeh, Hooman ;
Alavizadeh, Hootan ;
Jang-Jaccard, Julian .
COMPUTERS, 2022, 11 (03)
[2]  
Beechey Daniel, P MACHINE LEARNING R
[3]   Anomaly Detection: A Survey [J].
Chandola, Varun ;
Banerjee, Arindam ;
Kumar, Vipin .
ACM COMPUTING SURVEYS, 2009, 41 (03)
[4]  
Chimphlee Witcha, 2023, International Journal of Computer Networks Communications, V15, P73
[5]  
Estevez-Tapiador J. M., 2004, ACM Computing Surveys (CSUR), V36, P235
[6]   Anomaly-based network intrusion detection: Techniques, systems and challenges [J].
Garcia-Teodoro, P. ;
Diaz-Verdejo, J. ;
Macia-Fernandez, G. ;
Vazquez, E. .
COMPUTERS & SECURITY, 2009, 28 (1-2) :18-28
[7]  
Graham Emma, 2023, P 2023 INT C CYB, DOI [10.1109/ICCS.2023.983451, DOI 10.1109/ICCS.2023.983451]
[8]   Survey of intrusion detection systems: techniques, datasets and challenges [J].
Khraisat, Ansam ;
Gondal, Iqbal ;
Vamplew, Peter ;
Kamruzzaman, Joarder .
CYBERSECURITY, 2019, 2 (01)
[9]   Human-level control through deep reinforcement learning [J].
Mnih, Volodymyr ;
Kavukcuoglu, Koray ;
Silver, David ;
Rusu, Andrei A. ;
Veness, Joel ;
Bellemare, Marc G. ;
Graves, Alex ;
Riedmiller, Martin ;
Fidjeland, Andreas K. ;
Ostrovski, Georg ;
Petersen, Stig ;
Beattie, Charles ;
Sadik, Amir ;
Antonoglou, Ioannis ;
King, Helen ;
Kumaran, Dharshan ;
Wierstra, Daan ;
Legg, Shane ;
Hassabis, Demis .
NATURE, 2015, 518 (7540) :529-533
[10]   Toward Generating a New Intrusion Detection Dataset and Intrusion Traffic Characterization [J].
Sharafaldin, Iman ;
Lashkari, Arash Habibi ;
Ghorbani, Ali A. .
ICISSP: PROCEEDINGS OF THE 4TH INTERNATIONAL CONFERENCE ON INFORMATION SYSTEMS SECURITY AND PRIVACY, 2018, :108-116