Reinforcement learning for feedback-enabled cyber resilience

Y Huang, L Huang, Q Zhu - Annual reviews in control, 2022 - Elsevier
The rapid growth in the number of devices and their connectivity has enlarged the attack
surface and made cyber systems more vulnerable. As attackers become increasingly …

Multi-agent reinforcement learning: Methods, applications, visionary prospects, and challenges

Z Zhou, G Liu, Y Tang - arxiv preprint arxiv:2305.10091, 2023 - arxiv.org
Multi-agent reinforcement learning (MARL) is a widely used Artificial Intelligence (AI)
technique. However, current studies and applications need to address its scalability, non …

A (dis-) information theory of revealed and unrevealed preferences: emerging deception and skepticism via theory of mind

N Alon, L Schulz, JS Rosenschein, P Dayan - Open Mind, 2023 - direct.mit.edu
In complex situations involving communication, agents might attempt to mask their
intentions, exploiting Shannon's theory of information as a theory of misinformation. Here …

New challenges in reinforcement learning: a survey of security and privacy

Y Lei, D Ye, S Shen, Y Sui, T Zhu, W Zhou - Artificial Intelligence Review, 2023 - Springer
Reinforcement learning is one of the most important branches of AI. Due to its capacity for
self-adaption and decision-making in dynamic environments, reinforcement learning has …

adaparl: Adaptive privacy-aware reinforcement learning for sequential decision making human-in-the-loop systems

M Taherisadr, SA Stavroulakis, S Elmalaki - Proceedings of the 8th ACM …, 2023 - dl.acm.org
Reinforcement learning (RL) presents numerous benefits compared to rule-based
approaches in various applications. Privacy concerns have grown with the widespread use …

Security and Privacy Issues in Deep Reinforcement Learning: Threats and Countermeasures

K Mo, P Ye, X Ren, S Wang, W Li, J Li - ACM Computing Surveys, 2024 - dl.acm.org
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 …

Deceptive path planning via count-based reinforcement learning under specific time constraint

D Chen, Y Zeng, Y Zhang, S Li, K Xu, Q Yin - Mathematics, 2024 - mdpi.com
Deceptive path planning (DPP) aims to find a path that minimizes the probability of the
observer identifying the real goal of the observed before it reaches. It is important for …

Adversarial sampling-based motion planning

H Nichols, M Jimenez, Z Goddard… - IEEE Robotics and …, 2022 - ieeexplore.ieee.org
There are many scenarios in which a mobile agent may not want its path to be predictable.
Examples include preserving privacy or confusing an adversary. However, this desire for …

[PDF][PDF] Domain-Independent Deceptive Planning.

A Price, RF Pereira, P Masters, M Vered - AAMAS, 2023 - kclpure.kcl.ac.uk
The ability to deceive is a marker for human intelligence. It has been a central focus for
Artificial Intelligence (AI) since Turing's “Imitation Game”[51], that is, even before the term AI …

Deceptive reinforcement learning in model-free domains

A Lewis, T Miller - Proceedings of the International Conference on …, 2023 - ojs.aaai.org
This paper investigates deceptive reinforcement learning for privacy preservation in model-
free and continuous action space domains. In reinforcement learning, the reward function …