Security and Privacy Issues in Deep Reinforcement Learning: Threats and Countermeasures
Deep Reinforcement Learning (DRL) is an essential subfield of Artificial Intelligence (AI),
where agents interact with environments to learn policies for solving complex tasks. In recent …
where agents interact with environments to learn policies for solving complex tasks. In recent …
Differentially private reinforcement learning with linear function approximation
X Zhou - Proceedings of the ACM on Measurement and Analysis …, 2022 - dl.acm.org
Motivated by the wide adoption of reinforcement learning (RL) in real-world personalized
services, where users' sensitive and private information needs to be protected, we study …
services, where users' sensitive and private information needs to be protected, we study …
Shuffle private linear contextual bandits
SR Chowdhury, X Zhou - arXiv preprint arXiv:2202.05567, 2022 - arxiv.org
Differential privacy (DP) has been recently introduced to linear contextual bandits to formally
address the privacy concerns in its associated personalized services to participating users …
address the privacy concerns in its associated personalized services to participating users …
Distributed differential privacy in multi-armed bandits
SR Chowdhury, X Zhou - arXiv preprint arXiv:2206.05772, 2022 - arxiv.org
We consider the standard $ K $-armed bandit problem under a distributed trust model of
differential privacy (DP), which enables to guarantee privacy without a trustworthy server …
differential privacy (DP), which enables to guarantee privacy without a trustworthy server …
Offline reinforcement learning with differential privacy
The offline reinforcement learning (RL) problem is often motivated by the need to learn data-
driven decision policies in financial, legal and healthcare applications. However, the learned …
driven decision policies in financial, legal and healthcare applications. However, the learned …
Near-optimal differentially private reinforcement learning
Motivated by personalized healthcare and other applications involving sensitive data, we
study online exploration in reinforcement learning with differential privacy (DP) constraints …
study online exploration in reinforcement learning with differential privacy (DP) constraints …
Preserving Expert-Level Privacy in Offline Reinforcement Learning
The offline reinforcement learning (RL) problem aims to learn an optimal policy from
historical data collected by one or more behavioural policies (experts) by interacting with an …
historical data collected by one or more behavioural policies (experts) by interacting with an …
Differentially private exploration in reinforcement learning with linear representation
This paper studies privacy-preserving exploration in Markov Decision Processes (MDPs)
with linear representation. We first consider the setting of linear-mixture MDPs (Ayoub et al …
with linear representation. We first consider the setting of linear-mixture MDPs (Ayoub et al …
Privacy Preserving Reinforcement Learning for Population Processes
S Yang-Zhao, KS Ng - arXiv preprint arXiv:2406.17649, 2024 - arxiv.org
We consider the problem of privacy protection in Reinforcement Learning (RL) algorithms
that operate over population processes, a practical but understudied setting that includes, for …
that operate over population processes, a practical but understudied setting that includes, for …
Differentially private episodic reinforcement learning with heavy-tailed rewards
In this paper we study the problem of (finite horizon tabular) Markov decision processes
(MDPs) with heavy-tailed rewards under the constraint of differential privacy (DP) …
(MDPs) with heavy-tailed rewards under the constraint of differential privacy (DP) …