相关论文: On the Perturbed States for Transformed Input-robu…

Large transformer models pretrained on offline reinforcement learning datasets have demonstrated remarkable in-context reinforcement learning (ICRL) capabilities, where they can make good decisions when prompted with interaction…

Attacks on machine learning models have been extensively studied through stateless optimization. In this paper, we demonstrate how a reinforcement learning (RL) agent can learn a new class of attack algorithms that generate adversarial…

Model Inversion (MI) attacks aim to reconstruct private training data by abusing access to machine learning models. Contemporary MI attacks have achieved impressive attack performance, posing serious threats to privacy. Meanwhile, all…

Offline reinforcement learning (RL) presents a promising approach for learning reinforced policies from offline datasets without the need for costly or unsafe interactions with the environment. However, datasets collected by humans in…

Adversarial vulnerability remains a major obstacle to constructing reliable NLP systems. When imperceptible perturbations are added to raw input text, the performance of a deep learning model may drop dramatically under attacks. Recent work…

Deep Reinforcement Learning (RL) agents are susceptible to adversarial noise in their observations that can mislead their policies and decrease their performance. However, an adversary may be interested not only in decreasing the reward,…

Adversarial training in reinforcement learning (RL) is challenging because perturbations cascade through trajectories and compound over time, making fixed-strength attacks either overly destructive or too conservative. We propose…

Reinforcement Learning (RL) has achieved remarkable success in sequential decision tasks. However, recent studies have revealed the vulnerability of RL policies to different perturbations, raising concerns about their effectiveness and…

Reinforcement Learning (RL) and Multi-Agent Reinforcement Learning (MARL) have emerged as promising methodologies for addressing challenges in automated cyber defence (ACD). These techniques offer adaptive decision-making capabilities in…

In this paper, we propose a fast reinforcement learning (RL) control algorithm that enables online control of large-scale networked dynamic systems. RL is an effective way of designing model-free linear quadratic regulator (LQR) controllers…

Deep reinforcement learning (RL) policies are known to be vulnerable to adversarial perturbations to their observations, similar to adversarial examples for classifiers. However, an attacker is not usually able to directly modify another…

Deep reinforcement learning (DRL) has recently been used to perform efficient resource allocation in wireless communications. In this paper, the vulnerabilities of such DRL agents to adversarial attacks is studied. In particular, we…

Reinforcement learning (RL) has advanced greatly in the past few years with the employment of effective deep neural networks (DNNs) on the policy networks. With the great effectiveness came serious vulnerability issues with DNNs that small…

Given the success of reinforcement learning (RL) in various domains, it is promising to explore the application of its methods to the development of intelligent and autonomous cyber agents. Enabling this development requires a…

Reinforcement Learning (RL), bolstered by the expressive capabilities of Deep Neural Networks (DNNs) for function approximation, has demonstrated considerable success in numerous applications. However, its practicality in addressing various…

Successful applications of reinforcement learning in real-world problems often require dealing with partially observable states. It is in general very challenging to construct and infer hidden states as they often depend on the agent's…

This paper studies reinforcement learning (RL) under malicious falsification on cost signals and introduces a quantitative framework of attack models to understand the vulnerabilities of RL. Focusing on $Q$-learning, we show that…

Cyber-attacks are becoming increasingly sophisticated and frequent, highlighting the importance of network intrusion detection systems. This paper explores the potential and challenges of using deep reinforcement learning (DRL) in network…

Safe interaction with the environment is one of the most challenging aspects of Reinforcement Learning (RL) when applied to real-world problems. This is particularly important when unsafe actions have a high or irreversible negative impact…

We investigate robust model-free reinforcement learning algorithms designed for environments that may be dynamic or even adversarial. Traditional state-based policies often struggle to accommodate the challenges imposed by the presence of…