Logan Luna, a Ph.D. student at Embry-Riddle Aeronautical University, Daytona Beach, FL was this year’s winner of the IEEE-HKN Best Paper Award presented on 29 March 2025 for his paper entitled, “Dueling Deep Q-Learning for Intrusion Detection.” The IEEE-HKN Best Student Paper Award is presented annually at the Region 3 Technical Conference, SoutheastCon. The 2025 conference was held in Charlotte, North Carolina with the theme “Engineering the Future.” The primary and presenting author must be a student. Of the papers submitted, five finalists were selected. Each author presented their paper to a panel of judges. Regarding receiving this award for his work, Luna states, “Winning the IEEE HKN Best Student Paper Award means a great deal to me, especially as this was my first publication and I was naturally nervous about its submission. Having it be so well received, getting to present alongside such talented researchers, and ultimately being recognized with this award has been incredibly rewarding, making me even more excited for the work ahead.” For his achievement, Luna will receive a check for $500. IEEE-Eta Kappa Nu Best Student Paper Award was established by a generous donation by Dr. Hulya Kirkici and the IEEE Power Modulator Conference.
Here is the abstract of the winning paper:
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.
