Autonomous Response and Recovery in Large Industrial Control Networks with Deep Reinforcement Learning

Home

Discover

Bookmarks

Keep Up With Latest Trending Papers. Computer Science, AI and more.Subscribe

CC BY

Source arXiv

Machine Learning

Artificial Intelligence

Cryptography and Security

Autonomous Response and Recovery in Large Industrial Control Networks with Deep Reinforcement Learning

Autonomous Attack Mitigation for Industrial Control Systems

We present a deep reinforcement learning approach to autonomous response and recovery in large industrial control networks.

We propose an attention-based neural architecture that is flexible to the size of the network under protection.

To train and evaluate the autonomous defender agent, we present an industrial control network simulation environment suitable for reinforcement learning.

Experiments show that the learned agent can effectively mitigate advanced attacks that progress with few observable signals over several months before execution.

The proposed deep reinforcement learning approach outperforms a fully automated playbook method in simulation, taking less disruptive actions while also defending more nodes on the network.

Authors

John Mern, Kyle Hatch, Ryan Silva, Cameron Hickert, Tamim Sookoor, Mykel J. Kochenderfer

◐ Latest Activity

◐ Recommended Follows