This repository is based on my understanding and implementation of the algorithms published in Paper :
T. T. Nguyen and V. J. Reddi, "Deep Reinforcement Learning for Cyber Security," in IEEE Transactions on Neural Networks and Learning Systems, vol. 34, no. 8, pp. 3779-3795, Aug. 2023, doi: 10.1109/TNNLS.2021.3121870.
Abstract
The scale of Internet-connected systems has increased considerably, and these systems are being exposed to cyber attacks more than ever. The complexity and dynamics of cyber attacks require protecting mechanisms to be responsive, adaptive, and large-scale. Machine learning, or more specifi- cally deep reinforcement learning (DRL), methods have been proposed widely to address these issues. By incorporating deep learning into traditional RL, DRL is highly capable of solving complex, dynamic, and especially high-dimensional cyber defense problems. This paper presents a survey of DRL approaches developed for cyber security. We touch on different vital aspects, including DRL-based security methods for cyber-physical systems, autonomous intrusion detection techniques, and multi-agent DRL-based game theory simulations for defense strategies against cyber attacks. Extensive discussions and future research directions on DRL-based cyber security are also given. We expect that this comprehensive review provides the foundations for and facilitates future studies on exploring the potential of emerging DRL to cope with increasingly complex cyber security problems.
Literature Reviews
1. DRL In Cyber-Security : A Survey
1.a Security Methods for Cyber-Physical Systems
1.b Intrusion Detection Systems
1.b.a Host Based
1.b.b Network Based
1.c.a Jamming Attacks
1.c.b Spoofing Attacks
1.c.c Malware Attacks
Cyber Physical Systems
CPS in DRL
Game Theory
Hotbooting Method
Anti-Jamming Communications in WACRs
Smart Jammers
Frequency Spatial Anti-Jamming
Intrusion Detection Systems
IDS for WSNs
SARSA
