Related papers: Adversarial Inception Backdoor Attacks against Rei…
Recent work has demonstrated robust mechanisms by which attacks can be orchestrated on machine learning models. In contrast to adversarial examples, backdoor or trojan attacks embed surgically modified samples with targeted labels in the…
We study black-box reward poisoning attacks against reinforcement learning (RL), in which an adversary aims to manipulate the rewards to mislead a sequence of RL agents with unknown algorithms to learn a nefarious policy in an environment…
Most known regret bounds for reinforcement learning are either episodic or assume an environment without traps. We derive a regret bound without making either assumption, by allowing the algorithm to occasionally delegate an action to an…
This paper presents the first model extraction attack against Deep Reinforcement Learning (DRL), which enables an external adversary to precisely recover a black-box DRL model only from its interaction with the environment. Model extraction…
Backdoor attack has emerged as a major security threat to deep neural networks (DNNs). While existing defense methods have demonstrated promising results on detecting or erasing backdoors, it is still not clear whether robust training…
To ensure the usefulness of Reinforcement Learning (RL) in real systems, it is crucial to ensure they are robust to noise and adversarial attacks. In adversarial RL, an external attacker has the power to manipulate the victim agent's…
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,…
Deep reinforcement learning has shown promising results in learning control policies for complex sequential decision-making tasks. However, these neural network-based policies are known to be vulnerable to adversarial examples. This…
Development of autonomous cyber system defense strategies and action recommendations in the real-world is challenging, and includes characterizing system state uncertainties and attack-defense dynamics. We propose a data-driven deep…
Embodied agents, such as robots and virtual characters, must continuously select actions to execute tasks effectively, solving complex sequential decision-making problems. Given the difficulty of designing such controllers manually,…
Deep reinforcement learning (DRL) has become a powerful tool for complex decision-making in machine learning and AI. However, traditional methods often assume perfect action execution, overlooking the uncertainties and deviations between an…
The dangers of adversarial attacks on Uncrewed Aerial Vehicle (UAV) agents operating in public are increasing. Adopting AI-based techniques and, more specifically, Deep Learning (DL) approaches to control and guide these UAVs can be…
Deep neural networks are vulnerable to adversarial attacks, such as backdoor attacks in which a malicious adversary compromises a model during training such that specific behaviour can be triggered at test time by attaching a specific word…
Contrastive Learning (CL) has attracted enormous attention due to its remarkable capability in unsupervised representation learning. However, recent works have revealed the vulnerability of CL to backdoor attacks: the feature extractor…
Recent advances in artificial intelligence and the increasing need for powerful defensive measures in the domain of network security, have led to the adoption of deep learning approaches for use in network intrusion detection systems. These…
Adoption of machine learning (ML)-enabled cyber-physical systems (CPS) are becoming prevalent in various sectors of modern society such as transportation, industrial, and power grids. Recent studies in deep reinforcement learning (DRL) have…
Recent adversarial attack developments have made reinforcement learning more vulnerable, and different approaches exist to deploy attacks against it, where the key is how to choose the right timing of the attack. Some work tries to design…
A backdoor attack allows a malicious user to manipulate the environment or corrupt the training data, thus inserting a backdoor into the trained agent. Such attacks compromise the RL system's reliability, leading to potentially catastrophic…
The safety of decentralized reinforcement learning (RL) is a challenging problem since malicious agents can share their poisoned policies with benign agents. The paper investigates a cooperative backdoor attack in a decentralized…
Large amounts of incremental learning algorithms have been proposed to alleviate the catastrophic forgetting issue arises while dealing with sequential data on a time series. However, the adversarial robustness of incremental learners has…