Reinforcement Learning for Autonomous Defence in Software-Defined Networking

2018/08/17 by Yi Han, Benjamin I. P. Rubinstein, Han, Yi +15 · 3 citations
Computer Science · Mathematics · #Advanced Malware Detection Techniques #Adversarial Robustness in Machine Learning #Artificial Intelligence (cs.AI) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Physical Unclonable Functions (PUFs) and Hardware Security #cs.AI #cs.CR #cs.LG #stat.ML

paper · pdf · doi:10.48550/arxiv.1808.05770

20 pages, 8 figures

arxiv created 2018/08/17 · openalex publication_date 2018/08/17 · arxiv updated 2018/08/20 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Despite the successful application of machine learning (ML) in a wide range of domains, adaptability---the very property that makes machine learning desirable---can be exploited by adversaries to contaminate training and evade classification. In this paper, we investigate the feasibility of applying a specific class of machine learning algorithms, namely, reinforcement learning (RL) algorithms, for autonomous cyber defence in software-defined networking (SDN). In particular, we focus on how an RL agent reacts towards different forms of causative attacks that poison its training process, including indiscriminate and targeted, white-box and black-box attacks. In addition, we also study the impact of the attack timing, and explore potential countermeasures such as adversarial training.

Citations

• Prioritized Experience Replay
• Curie: A method for protecting SVM Classifier from Poisoning Attack
• Data Poisoning Attacks on Factorization-Based Collaborative Filtering
• Blocking Transferability of Adversarial Examples in Black-Box Learning Systems
• Keeping the Bad Guys Out: Protecting and Vaccinating Deep Learning with JPEG Compression
• Certified Defenses for Data Poisoning Attacks
• Practical Black-Box Attacks against Machine Learning
• Improving the Robustness of Deep Neural Networks via Stability Training
• Universal adversarial perturbations

Cited by

• Online Incident Response Planning under Model Misspecification through Bayesian Learning and Belief Quantization
• Position: Certified Robustness Does Not (Yet) Imply Model Security
• Physics-Informed Graph Neural Networks for Attack Path Prediction

Related

• Adversarial Deep Reinforcement Learning for Cyber Security in Software Defined Networks
• AdaDoS: Adaptive DoS Attack via Deep Adversarial Reinforcement Learning in SDN
• Adversarial Reinforcement Learning under Partial Observability in Autonomous Computer Network Defence
• Deep Reinforcement Learning for Autonomous Cyber Defence: A Survey
• Inroads into Autonomous Network Defence using Explained Reinforcement Learning