相关论文: Optimal Zero-Shot Detector for Multi-Armed Attacks

This paper introduces the first asymptotically optimal strategy for a multi armed bandit (MAB) model under side constraints. The side constraints model situations in which bandit activations are limited by the availability of certain…

Developing reliable defenses against patch attacks on object detectors has attracted increasing interest. However, we identify that existing defense evaluations lack a unified and comprehensive framework, resulting in inconsistent and…

Currently the Dempster-Shafer based algorithm and Uniform Random Probability based algorithm are the preferred method of resolving security games, in which defenders are able to identify attackers and only strategy remained ambiguous.…

Data sharing between different organizations is an essential process in today's connected world. However, recently there were many concerns about data sharing as sharing sensitive information can jeopardize users' privacy. To preserve the…

In modern transportation networks, adversaries can manipulate routing algorithms using false data injection attacks, such as simulating heavy traffic with multiple devices running crowdsourced navigation applications, to mislead vehicles…

Over the years, most research towards defenses against adversarial attacks on machine learning models has been in the image recognition domain. The ML-based malware detection domain has received less attention despite its importance.…

This paper proposes an encrypted state observer that is capable of detecting sensor attacks without decryption. We first design a state observer that operates over a finite field of integers with the modular arithmetic. The observer…

Similar to a strategic interaction between rational and intelligent agents, cryptography problems can be examined through the prism of game theory. In this setting, the agent aiming to protect a message is called the defender, while the one…

Collaborative multi-agent reinforcement learning has rapidly evolved, offering state-of-the-art algorithms for real-world applications, including sensitive domains. However, a key challenge to its widespread adoption is the lack of a…

We study best-arm identification in stochastic multi-armed bandits under the fixed-confidence setting, focusing on instances with multiple optimal arms. Unlike prior work that addresses the unknown-number-of-optimal-arms case, we consider…

An information-theoretic approach is proposed to watermark embedding and detection under limited detector resources. First, we consider the attack-free scenario under which asymptotically optimal decision regions in the Neyman-Pearson sense…

Back-door attack poses a severe threat to deep learning systems. It injects hidden malicious behaviors to a model such that any input stamped with a special pattern can trigger such behaviors. Detecting back-door is hence of pressing need.…

In this paper, we consider a robust action selection problem in multi-agent systems where performance must be guaranteed when the system suffers a worst-case attack on its agents. Specifically, agents are tasked with selecting actions from…

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…

Protecting personal data against exploitation of machine learning models is crucial. Recently, availability attacks have shown great promise to provide an extra layer of protection against the unauthorized use of data to train neural…

As large language models are increasingly deployed in sensitive environments, fingerprinting attacks pose significant privacy and security risks. We present a study of LLM fingerprinting from both offensive and defensive perspectives. Our…

This work focuses on the problem of distributed optimization in multi-agent cyberphysical systems, where a legitimate agent's iterates are influenced both by the values it receives from potentially malicious neighboring agents, and by its…

Moving target defense (MTD) is a proactive defense approach that aims to thwart attacks by continuously changing the attack surface of a system (e.g., changing host or network configurations), thereby increasing the adversary's uncertainty…

Deep Learning algorithms have achieved the state-of-the-art performance for Image Classification and have been used even in security-critical applications, such as biometric recognition systems and self-driving cars. However, recent works…

Data attacks on meter measurements in the power grid can lead to errors in state estimation. This paper presents a new data attack model where an adversary produces changes in state estimation despite failing bad-data detection checks. The…