Deep Reinforcement Learning for Cyber Security

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 scalable. Machine learning, or more specifically 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 multiagent 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.

References in corpus (26)

• A Brief Survey of Deep Reinforcement Learning
• Deep Reinforcement Learning for Multi-Agent Systems: A Review of Challenges, Solutions and Applications
• Deep Reinforcement Learning for De-Novo Drug Design
• Applications of Deep Learning and Reinforcement Learning to Biological Data
• Human-level performance in first-person multiplayer games with population-based deep reinforcement learning
• StarCraft II: A New Challenge for Reinforcement Learning
• Neuro-memristive Circuits for Edge Computing: A review
• Distributed Distributional Deterministic Policy Gradients
• Bridging the Gap Between Value and Policy Based Reinforcement Learning
• Relational Deep Reinforcement Learning
• A Multi-Objective Deep Reinforcement Learning Framework
• LSTM-Based System-Call Language Modeling and Robust Ensemble Method for Designing Host-Based Intrusion Detection Systems
• Variance Reduction for Policy Gradient with Action-Dependent Factorized Baselines
• Learning model-based planning from scratch
• IoT Security Techniques Based on Machine Learning
• Falsification of Cyber-Physical Systems Using Deep Reinforcement Learning
• TStarBots: Defeating the Cheating Level Builtin AI in StarCraft II in the Full Game
• A New Tensioning Method using Deep Reinforcement Learning for Surgical Pattern Cutting
• Game Theory Meets Network Security: A Tutorial at ACM CCS
• A Human Mixed Strategy Approach to Deep Reinforcement Learning
• A short review on Applications of Deep learning for Cyber security
• Deep Reinforcement Learning for Detecting Malicious Websites
• Multi-Agent Deep Reinforcement Learning with Human Strategies
• Adversarial Reinforcement Learning for Observer Design in Autonomous Systems under Cyber Attacks
• On Reinforcement Learning for Full-length Game of StarCraft
• Stealthy and Efficient Adversarial Attacks against Deep Reinforcement Learning

Cited by in corpus (40)

• A Review of Deep Reinforcement Learning for Smart Building Energy Management
• The Role of Machine Learning in Cybersecurity
• Utilising Deep Learning Techniques for Effective Zero-Day Attack Detection
• Reinforcement Learning for IoT Security: A Comprehensive Survey
• Machine Learning for Security in Vehicular Networks: A Comprehensive Survey
• Machine and Deep Learning for IoT Security and Privacy: Applications, Challenges, and Future Directions
• Finding Effective Security Strategies through Reinforcement Learning and Self-Play
• Towards an AI-Enhanced Cyber Threat Intelligence Processing Pipeline
• Deep Learning Methods for Credit Card Fraud Detection
• Deep Reinforcement Learning for Cybersecurity Threat Detection and Protection: A Review
• Autonomous Network Defence using Reinforcement Learning
• Vision-based Learning for Drones: A Survey
• Adaptive Anomaly Detection for Identifying Attacks in Cyber-Physical Systems: A Systematic Literature Review
• Examining the Differential Risk from High-level Artificial Intelligence and the Question of Control
• Learning Near-Optimal Intrusion Responses Against Dynamic Attackers
• DOLOS: A Novel Architecture for Moving Target Defense
• DETERRENT: Detecting Trojans using Reinforcement Learning
• Log-law recovery through reinforcement-learning wall model for large-eddy simulation
• Intrusion Prevention through Optimal Stopping
• Model-Based Multi-Agent RL in Zero-Sum Markov Games with Near-Optimal Sample Complexity
• Prospective Artificial Intelligence Approaches for Active Cyber Defence
• Learning Intrusion Prevention Policies through Optimal Stopping
• SquirRL: Automating Attack Analysis on Blockchain Incentive Mechanisms with Deep Reinforcement Learning
• CyGIL: A Cyber Gym for Training Autonomous Agents over Emulated Network Systems
• Automating Privilege Escalation with Deep Reinforcement Learning
• Trojan Playground: A Reinforcement Learning Framework for Hardware Trojan Insertion and Detection
• Automated Security Response through Online Learning with Adaptive Conjectures
• Deception in Social Learning: A Multi-Agent Reinforcement Learning Perspective
• Discovering Command and Control Channels Using Reinforcement Learning
• The Power of MEME: Adversarial Malware Creation with Model-Based Reinforcement Learning
• AI-Driven Container Security Approaches for 5G and Beyond: A Survey
• Canaries and Whistles: Resilient Drone Communication Networks with (or without) Deep Reinforcement Learning
• Leveraging AI and Intelligent Reflecting Surface for Energy-Efficient Communication in 6G IoT
• Discovering Command and Control (C2) Channels on Tor and Public Networks Using Reinforcement Learning
• Constraints Satisfiability Driven Reinforcement Learning for Autonomous Cyber Defense
• LiPar: A Lightweight Parallel Learning Model for Practical In-Vehicle Network Intrusion Detection
• Review, Analysis and Design of a Comprehensive Deep Reinforcement Learning Framework
• Reinforcement Learning for Intelligent Healthcare Systems: A Comprehensive Survey
• Reinforcement Learning for Industrial Control Network Cyber Security Orchestration
• A Differentially Private Game Theoretic Approach for Deceiving Cyber Adversaries