Metrics
9 Record Views
Conference proceeding
Neuro-Symbolic Integration for Open Set Recognition in Network Intrusion Detection
AIxIA 2024 – Advances in Artificial Intelligence, Vol.15450, pp.50-63
Lecture Notes in Artificial Intelligence
International Conference of the Italian Association for Artificial Intelligence, XXIIIrd (Bolzano, Italy, 11/25/2024–11/28/2024)
01/01/2025
Web of Science ID: WOS:001532132700005
Abstract
Open Set Recognition (OSR) addresses the challenge of classifying inputs into known and unknown categories, a crucial task where labeling is often prohibitively expensive or incomplete. This is particularly vital in applications like Network Intrusion Detection Systems (NIDS), where OSR is used to identify novel, previously unknown attacks. We propose a neuro-symbolic integration approach that combines deep learning and symbolic methods, enhancing deep embedding for clustering with custom loss functions and leveraging XGBoost's decision tree algorithms. Our methodology not only robustly addresses the identification of previously unknown attacks in NIDS but also effectively manages scenarios involving covariance shift. We demonstrate the efficacy of our approach through extensive experimentation, achieving an AUROC of 0.99 in both contexts. This paper presents a significant step forward in OSR for network intrusion detection by integrating deep and symbolic learning to handle unforeseen challenges in dynamic environments.
Related links
Details
- Title
- Neuro-Symbolic Integration for Open Set Recognition in Network Intrusion Detection
- Publication Details
- AIxIA 2024 – Advances in Artificial Intelligence, Vol.15450, pp.50-63
- Resource Type
- Conference proceeding
- Conference
- International Conference of the Italian Association for Artificial Intelligence, XXIIIrd (Bolzano, Italy, 11/25/2024–11/28/2024)
- Publisher
- Springer Nature; Cham
- Series
- Lecture Notes in Artificial Intelligence
- Number of pages
- 14
- Grant note
- W911NF-23-2-0108 / U.S. Military Academy (USMA) USMA 21050 / U.S. Army Combat Capabilities Development Command Army Research Laboratory 341; PE00000013 / Italian Ministry of University and Research through PNRR - M4C2 - Investimento 1.3 (Decreto Direttoriale MUR) - European Union under the NextGeneration EU programme; Ministry of Education, Universities and Research (MIUR) USMA 23004 / Defense Advanced Research Projects Agency; United States Department of Defense; Defense Advanced Research Projects Agency (DARPA)
- Copyright
- © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2025
- Identifiers
- WOS:001532132700005; 99381512427906600
- Academic Unit
- Intelligent Systems and Robotics; Hal Marcus College of Science and Engineering
- Language
- English