6 accepted papers
Recent years have seen an explosion of interest in autonomous cyber defence agents trained to defend computer networks using deep reinforcement learning. These agents are typically trained in cyber gym environments using dense, highly engineered reward functions which combine many penalties and ince…
Deep Reinforcement Learning (DRL) systems are increasingly used in safety-critical applications, yet their security remains severely underexplored. This work investigates backdoor attacks, which implant hidden triggers that cause malicious actions only when specific inputs appear in the observation
Malware detection in real-world settings must deal with evolving threats, limited labeling budgets, and uncertain predictions. Traditional classifiers, without additional mechanisms, struggle to maintain performance under concept drift in malware domains, as their supervised learning formulation can
Statistical parity is one of the most foundational constraints in algorithmic fairness and privacy. In this paper, we show that statistical parity can be enforced efficiently in the contextual bandit setting while retaining strong performance guarantees. Specifically, we present a meta-algorithm tha…
We consider the classic problem of online convex optimisation. Whereas the notion of static regret is relevant for stationary problems, the notion of switching regret is more appropriate for non-stationary problems. A switching regret is defined relative to any segmentation of the trial sequence, an…
In this paper we adapt the nearest neighbour rule to the contextual bandit problem. Our algorithm handles the fully adversarial setting in which no assumptions at all are made about the data-generation process. When combined with a sufficiently fast data-structure for (perhaps approximate) adaptive…