A Bio-Inspired Deep Learning Intrusion Detection Framework for Cyber-Physical System Security
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
This work presents a bio-inspired deep learning-based intrusion detection framework for enhancing cybersecurity in cyber-physical systems (CPS). The proposed approach integrates a Multi-Objective Biogeography-Based Optimization (MOBO) algorithm for feature selection with a hybrid Support Vector Machine and Deep Recurrent Neural Network (SVM-DRNN) model for intrusion detection. The framework is evaluated on benchmark datasets including NSLKDD2015 and CICIDS2015, achieving high detection accuracy (up to 99.4%) and strong generalization performance across diverse attack scenarios. The model demonstrates effectiveness in identifying complex cyber threats such as advanced persistent threats and anomaly-based attacks in CPS environments. Keywords: Explainable AI, Cybersecurity, Intrusion Detection Systems, Cyber-Physical Systems, Deep Learning, Feature Optimization, Autonomous Security Systems.
Fields of Study & Subjects
Network Security and Intrusion Detection
Network Packet Processing and Optimization
Artificial Immune Systems Applications
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 28 March 2026
- Language
- EN