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 …
White-box adversarial policies in deep reinforcement learning
In reinforcement learning (RL), adversarial policies can be developed by training an
adversarial agent to minimize a target agent's rewards. Prior work has studied black-box …
adversarial agent to minimize a target agent's rewards. Prior work has studied black-box …
Ad hoc teamwork in the presence of adversaries
T Fujimoto, S Chatterjee, A Ganguly - arXiv preprint arXiv:2208.05071, 2022 - arxiv.org
Advances in ad hoc teamwork have the potential to create agents that collaborate robustly in
real-world applications. Agents deployed in the real world, however, are vulnerable to …
real-world applications. Agents deployed in the real world, however, are vulnerable to …
Assessing the Impact of Distribution Shift on Reinforcement Learning Performance
T Fujimoto, J Suetterlein, S Chatterjee… - arXiv preprint arXiv …, 2024 - arxiv.org
Research in machine learning is making progress in fixing its own reproducibility crisis.
Reinforcement learning (RL), in particular, faces its own set of unique challenges …
Reinforcement learning (RL), in particular, faces its own set of unique challenges …
[PDF][PDF] Red teaming with mind reading: White-box adversarial policies against rl agents
Adversarial examples can be useful for identifying vulnerabilities in AI systems before they
are deployed. In reinforcement learning (RL), adversarial policies can be developed by …
are deployed. In reinforcement learning (RL), adversarial policies can be developed by …