Mitigating Deep Reinforcement Learning Backdoors in the Neural Activation Space

This paper investigates the threat of backdoors in Deep Reinforcement Learning (DRL) agent policies and proposes a novel method for their detection at runtime. Our study focuses on elusive in-distribution backdoor triggers. Such triggers are designed to induce a deviation in the behaviour of a backdoored agent while blending into the expected data distribution to evade detection. Through experiments conducted in the Atari Breakout environment, we demonstrate the limitations of current sanitisation methods when faced with such triggers and investigate why they present a challenging defence problem. We then evaluate the hypothesis that backdoor triggers might be easier to detect in the neural activation space of the DRL agent's policy network. Our statistical analysis shows that indeed the activation patterns in the agent's policy network are distinct in the presence of a trigger, regardless of how well the trigger is concealed in the environment. Based on this, we propose a new defence approach that uses a classifier trained on clean environment samples and detects abnormal activations. Our results show that even lightweight classifiers can effectively prevent malicious actions with considerable accuracy, indicating the potential of this research direction even against sophisticated adversaries.

Automated Cyber Defence: A Review

Within recent times, cybercriminals have curated a variety of organised and resolute cyber attacks within a range of cyber systems, leading to consequential ramifications to private and governmental institutions. Current security-based automation and orchestrations focus on automating fixed purpose and hard-coded solutions, which are easily surpassed by modern-day cyber attacks. Research within Automated Cyber Defence will allow the development and enabling intelligence response by autonomously defending networked systems through sequential decision-making agents. This article comprehensively elaborates the developments within Automated Cyber Defence through a requirement analysis divided into two sub-areas, namely, automated defence and attack agents and Autonomous Cyber Operation (ACO) Gyms. The requirement analysis allows the comparison of automated agents and highlights the importance of ACO Gyms for their continual development. The requirement analysis is also used to critique ACO Gyms with an overall aim to develop them for deploying automated agents within real-world networked systems. Relevant future challenges were addressed from the overall analysis to accelerate development within the area of Automated Cyber Defence.