Adversarial Reinforcement Learning under Partial Observability in Autonomous Computer Network Defence
Preprint
Abstract
Recent studies have demonstrated that reinforcement learning (RL) agents are susceptible to adversarial manipulation, similar to vulnerabilities previously demonstrated in the supervised learning setting. While most existing work studies the problem in the context of computer vision or console games, this paper focuses on reinforcement learning in autonomous cyber defence under partial observability. We demonstrate that under the black-box setting, where the attacker has no direct access to the target RL model, causative attacks---attacks that target the training process---can poison RL agents even if the attacker only has partial observability of the environment. In addition, we propose an inversion defence method that aims to apply the opposite perturbation to that which an attacker might use to generate their adversarial samples. Our experimental results illustrate that the countermeasure can effectively reduce the impact of the causative attack, while not significantly affecting the training process in non-attack scenarios.Keywords
All Related Versions
This publication has 10 references indexed in Scilit:
- Robust Deep Reinforcement Learning with Adversarial Attacks2018
- Adversarially Robust Policy Learning: Active construction of physically-plausible perturbations2017
- Tactics of Adversarial Attack on Deep Reinforcement Learning Agents2017
- Vulnerability of Deep Reinforcement Learning to Policy Induction Attacks2017
- Towards Evaluating the Robustness of Neural Networks2017
- Practical Black-Box Attacks against Machine Learning2017
- DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks2016
- The Limitations of Deep Learning in Adversarial Settings2016
- Deep Reinforcement Learning with Double Q-LearningProceedings of the AAAI Conference on Artificial Intelligence, 2016
- Deep neural networks are easily fooled: High confidence predictions for unrecognizable images2015