相关论文: Provably Efficient Black-Box Action Poisoning Atta…

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…

Despite the successful application of machine learning (ML) in a wide range of domains, adaptability---the very property that makes machine learning desirable---can be exploited by adversaries to contaminate training and evade…

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…

Poisoning attacks on Reinforcement Learning (RL) systems could take advantage of RL algorithm's vulnerabilities and cause failure of the learning. However, prior works on poisoning RL usually either unrealistically assume the attacker knows…

We study a security threat to batch reinforcement learning and control where the attacker aims to poison the learned policy. The victim is a reinforcement learner / controller which first estimates the dynamics and the rewards from a batch…

Reinforcement learning (RL) has achieved remarkable success in fields like robotics and autonomous driving, but adversarial attacks designed to mislead RL systems remain challenging. Existing approaches often rely on modifying the…

Adversarial attacks on video recognition models have been explored recently. However, most existing works treat each video frame equally and ignore their temporal interactions. To overcome this drawback, a few methods try to select some key…

In targeted poisoning attacks, an attacker manipulates an agent-environment interaction to force the agent into adopting a policy of interest, called target policy. Prior work has primarily focused on attacks that modify standard MDP…

Neural contextual bandits are vulnerable to adversarial attacks, where subtle perturbations to rewards, actions, or contexts induce suboptimal decisions. We introduce AdvBandit, a black-box adaptive attack that formulates context poisoning…

Despite recent advancements in Large Language Models (LLMs) and their alignment, they can still be jailbroken, i.e., harmful and toxic content can be elicited from them. While existing red-teaming methods have shown promise in uncovering…

Recent advancements in Reinforcement Learning with Human Feedback (RLHF) have significantly impacted the alignment of Large Language Models (LLMs). The sensitivity of reinforcement learning algorithms such as Proximal Policy Optimization…

The success of deep learning research has catapulted deep models into production systems that our society is becoming increasingly dependent on, especially in the image and video domains. However, recent work has shown that these largely…

We study reward poisoning attacks on online deep reinforcement learning (DRL), where the attacker is oblivious to the learning algorithm used by the agent and the dynamics of the environment. We demonstrate the intrinsic vulnerability of…

Reinforcement Learning with Human Feedback (RLHF) is a methodology designed to align Large Language Models (LLMs) with human preferences, playing an important role in LLMs alignment. Despite its advantages, RLHF relies on human annotators…

Recent research has confirmed the feasibility of backdoor attacks in deep reinforcement learning (RL) systems. However, the existing attacks require the ability to arbitrarily modify an agent's observation, constraining the application…

The financial industry relies on deep learning models for making important decisions. This adoption brings new danger, as deep black-box models are known to be vulnerable to adversarial attacks. In computer vision, one can shape the output…

To understand the security threats to reinforcement learning (RL) algorithms, this paper studies poisoning attacks to manipulate \emph{any} order-optimal learning algorithm towards a targeted policy in episodic RL and examines the potential…

Black-box adversarial attacks present a realistic threat to action recognition systems. Existing black-box attacks follow either a query-based approach where an attack is optimized by querying the target model, or a transfer-based approach…

Deep learning has made significant breakthroughs in many fields, including electroencephalogram (EEG) based brain-computer interfaces (BCIs). However, deep learning models are vulnerable to adversarial attacks, in which deliberately…

Reinforcement learning (RL) makes an agent learn from trial-and-error experiences gathered during the interaction with the environment. Recently, offline RL has become a popular RL paradigm because it saves the interactions with…