Inroads into Autonomous Network Defence using Explained Reinforcement Learning

by   Myles Foley, et al.
The Alan Turing Institute
Imperial College London

Computer network defence is a complicated task that has necessitated a high degree of human involvement. However, with recent advancements in machine learning, fully autonomous network defence is becoming increasingly plausible. This paper introduces an end-to-end methodology for studying attack strategies, designing defence agents and explaining their operation. First, using state diagrams, we visualise adversarial behaviour to gain insight about potential points of intervention and inform the design of our defensive models. We opt to use a set of deep reinforcement learning agents trained on different parts of the task and organised in a shallow hierarchy. Our evaluation shows that the resulting design achieves a substantial performance improvement compared to prior work. Finally, to better investigate the decision-making process of our agents, we complete our analysis with a feature ablation and importance study.


page 1

page 2

page 3

page 4


Poisoning Deep Reinforcement Learning Agents with In-Distribution Triggers

In this paper, we propose a new data poisoning attack and apply it to de...

Reinforcement Learning in Conflicting Environments for Autonomous Vehicles

In this work, we investigate the application of Reinforcement Learning t...

Motion Planning Among Dynamic, Decision-Making Agents with Deep Reinforcement Learning

Robots that navigate among pedestrians use collision avoidance algorithm...

Benchmarking Perturbation-based Saliency Maps for Explaining Deep Reinforcement Learning Agents

Recent years saw a plethora of work on explaining complex intelligent ag...

Decision-Making in Reinforcement Learning

In this research work, probabilistic decision-making approaches are stud...

Counterfactual States for Atari Agents via Generative Deep Learning

Although deep reinforcement learning agents have produced impressive res...

Improving Playtesting Coverage via Curiosity Driven Reinforcement Learning Agents

As modern games continue growing both in size and complexity, it has bec...

Please sign up or login with your details

Forgot password? Click here to reset