Quantum-Resistant Intrusion Detection Using Multi-Agent Reinforcement Learning

Abstract

The rising cyber threat complexity heightens the need for advanced Intrusion Detection Systems (IDSs) capable of swiftly identifying familiar and new attack methods, highlighting an urgent concern. Feature selection, by diminishing input features, boosting detection accuracy, and cutting computational time, significantly enhances machine learning-based IDS performance. To tackle these issues a model has developed QIDSMR caters to 6G-enabled Internet of Things (IoT), tackling quantum-attackers and network variations. A multi-slice 6G architecture with NEUROSAFE-6G, encompassing layers for security adaptability. The Threat Model addresses cryptographic vulnerabilities, integrity breaches, and diverse attacks from classical and quantum adversaries. IoT-Quantum Key Distribution (QKD) customizes key generation based on device capabilities and security needs. Quantum entropy and anomaly scores enhance detection in Q-IDS. Quantum Evolutionary Algorithms (QEA) utilizes probabilistic qubit encoding and gate adaptation for diversity. Integration of quantum entropy variations and anomaly scores improve detection efficiency. Energy-efficient interferometry aids intrusion detection. Hyperparameter optimization involves Convolutional Neural Network (CNN) classifiers and Quantum Particle Swarm Optimization (QPSO). A QCNN hybrid with variational quantum circuits detects complex attacks. Multi-Agent Reinforcement Learning strengthens detection methods. DSAC focuses on scalable deployment with energy-aware optimization and collaborative learning. The simulation parameters are detection accuracy, response time, attack detection delay, overhead, false positive rate, and communication overhead.