Multi-Agent Reinforcement Learning (MARL) is susceptible to Adversarial Machine Learning (AML) attacks. Execution-time AML attacks against MARL are complex due to effects that propagate across time and between agents. To understand the interaction between AML and MARL, this survey covers attacks and defences for MARL, Multi-Agent Learning (MAL), and Deep Reinforcement Learning (DRL). This survey proposes a novel perspective on AML attacks based on attack vectors. This survey also proposes a framework that addresses gaps in current modelling frameworks and enables the comparison of different attacks against MARL. Lastly, the survey identifies knowledge gaps and future avenues of research.
Organised attacks on a computer system to test existing defences, i.e., penetration testing, have been used extensively to evaluate network security. However, penetration testing is a time-consuming process. Additionally, establishing a strategy that resembles a real cyber-attack typically requires in-depth knowledge of the cybersecurity domain. This paper presents a novel architecture, named deep cascaded reinforcement learning agents, or CRLA, that addresses large discrete action spaces in an autonomous penetration testing simulator, where the number of actions exponentially increases with the complexity of the designed cybersecurity network. Employing an algebraic action decomposition strategy, CRLA is shown to find the optimal attack policy in scenarios with large action spaces faster and more stably than a conventional deep Q-learning agent, which is commonly used as a method for applying artificial intelligence to autonomous penetration testing.
Autonomous Cyber Operations (ACO) involves the consideration of blue team (defender) and red team (attacker) decision-making models in adversarial scenarios. To support the application of machine learning algorithms to solve this problem, and to encourage such practitioners to attend to problems in the ACO setting, a suitable gym (toolkit for experiments) is necessary. We introduce CybORG, a work-in-progress gym for ACO research. Driven by the need to efficiently support reinforcement learning to train adversarial decision-making models through simulation and emulation, our design differs from prior related work. Our early evaluation provides some evidence that CybORG is appropriate for our purpose and may provide a basis for advancing ACO research towards practical applications.