Related papers: Current injection and voltage insertion attacks ag…

A particularly successful detector blinding attack has been recently demonstrated on various quantum key distribution (QKD) systems, performing for the first time an undetectable and complete recovery of the key. In this paper two original…

The vulnerability of Vision Large Language Models (VLLMs) to jailbreak attacks appears as no surprise. However, recent defense mechanisms against these attacks have reached near-saturation performance on benchmark evaluations, often with…

Continuous-variable quantum key distribution (CV-QKD) is a quantum communication technology that offers an unconditional security guarantee. However, the practical deployment of CV-QKD systems remains vulnerable to various quantum attacks.…

Machine learning (ML) models that use deep neural networks are vulnerable to backdoor attacks. Such attacks involve the insertion of a (hidden) trigger by an adversary. As a consequence, any input that contains the trigger will cause the…

This paper studies a strategic security problem in networked control systems under stealthy false data injection attacks. The security problem is modeled as a bilateral cognitive security game between a defender and an adversary, each…

In this paper, we consider the problem of attack-resilient state estimation, that is to reliably estimate the true system states despite two classes of attacks: (i) attacks on the switching mechanisms and (ii) false data injection attacks…

Most security proofs of quantum key distribution (QKD) disregard the effect of information leakage from the users' devices, and, thus, do not protect against Trojan-horse attacks (THAs). In a THA, the eavesdropper injects strong light into…

Backdoor attacks on deep neural networks have emerged as significant security threats, especially as DNNs are increasingly deployed in security-critical applications. However, most existing works assume that the attacker has access to the…

Vision-Language Models (VLMs) have achieved remarkable performance on a variety of tasks, yet they remain vulnerable to jailbreak attacks that compromise safety and reliability. In this paper, we provide an information-theoretic framework…

Vision-language artificial intelligence models (VLMs) possess medical knowledge and can be employed in healthcare in numerous ways, including as image interpreters, virtual scribes, and general decision support systems. However, here, we…

Visual token compression is widely used to accelerate large vision-language models (LVLMs) by pruning or merging visual tokens, yet its adversarial robustness remains unexplored. We show that existing encoder-based attacks cannot fully…

Security requirements for the Internet of things (IoT), wireless sensor nodes, and other wireless devices connected in a network for data exchange are high. These devices are often subject to lab analysis with the objective to reveal secret…

Physical-layer group secret-key (GSK) generation is an effective way of generating secret keys in wireless networks, wherein the nodes exploit inherent randomness in the wireless channels to generate group keys, which are subsequently…

As large language models (LLMs) become integrated into various sensitive applications, prompt injection, the use of prompting to induce harmful behaviors from LLMs, poses an ever increasing risk. Prompt injection attacks can cause LLMs to…

In this paper, we survey the state of the art of the secure key exchange method that is secured by the laws of classical statistical physics, and involves the Kirchhoff's law and the generalized Johnson noise equation, too. We discuss the…

Quantum key distribution (QKD) provides a theoretically secure method for cryptographic key exchange by leveraging quantum mechanics, but practical implementations face vulnerabilities such as Trojan horse attack on phase modulators. This…

The proliferation of Large Language Models (LLMs) in diverse applications underscores the pressing need for robust security measures to thwart potential jailbreak attacks. These attacks exploit vulnerabilities within LLMs, endanger data…

Deep Learning (DL) is being applied in various domains, especially in safety-critical applications such as autonomous driving. Consequently, it is of great significance to ensure the robustness of these methods and thus counteract uncertain…

Large Language Models (LLMs) are vulnerable to prompt injection attacks, and several defenses have recently been proposed, often claiming to mitigate these attacks successfully. However, we argue that existing studies lack a principled…

We consider two-way continuous-variable quantum key distribution, studying its security against general eavesdropping strategies. Assuming the asymptotic limit of many signals exchanged, we prove that two-way Gaussian protocols are immune…