Zobrazeno 1 - 10
of 118
pro vyhledávání: '"Hicks, Chris"'
Publikováno v:
ASIA CCS '22: Proceedings of the 2022 ACM on Asia Conference on Computer and Communications Security
In the network security arms race, the defender is significantly disadvantaged as they need to successfully detect and counter every malicious attack. In contrast, the attacker needs to succeed only once. To level the playing field, we investigate th
Externí odkaz:
http://arxiv.org/abs/2409.18197
Multi-agent reinforcement learning (MARL) methods, while effective in zero-sum or positive-sum games, often yield suboptimal outcomes in general-sum games where cooperation is essential for achieving globally optimal outcomes. Matrix game social dile
Externí odkaz:
http://arxiv.org/abs/2408.02148
Publikováno v:
2024 IEEE Security and Privacy Workshops (SPW), pp. 76-86, 2024
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
Externí odkaz:
http://arxiv.org/abs/2407.15168
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 rela
Externí odkaz:
http://arxiv.org/abs/2405.20824
We study the problem of efficiently detecting Out-of-Distribution (OOD) samples at test time in supervised and unsupervised learning contexts. While ML models are typically trained under the assumption that training and test data stem from the same d
Externí odkaz:
http://arxiv.org/abs/2405.03052
In this paper we present fusion encoder networks (FENs): a class of algorithms for creating neural networks that map sequences to outputs. The resulting neural network has only logarithmic depth (alleviating the degradation of data as it propagates t
Externí odkaz:
http://arxiv.org/abs/2402.15883
In this paper we consider the adversarial contextual bandit problem in metric spaces. The paper "Nearest neighbour with bandit feedback" tackled this problem but when there are many contexts near the decision boundary of the comparator policy it suff
Externí odkaz:
http://arxiv.org/abs/2312.09332
Publikováno v:
In Proceedings of the 16th ACM Workshop on Artificial Intelligence and Security. Association for Computing Machinery, 91-101 (2023)
Communication networks able to withstand hostile environments are critically important for disaster relief operations. In this paper, we consider a challenging scenario where drones have been compromised in the supply chain, during their manufacture,
Externí odkaz:
http://arxiv.org/abs/2312.04940
As machine learning models become more capable, they have exhibited increased potential in solving complex tasks. One of the most promising directions uses deep reinforcement learning to train autonomous agents in computer network defense tasks. This
Externí odkaz:
http://arxiv.org/abs/2310.13565
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
Externí odkaz:
http://arxiv.org/abs/2306.13773