Related papers: Current injection and voltage insertion attacks ag…
This paper proposes a multi-mode Gaussian modulated continuous variable quantum key distribution (CV-QKD) scheme able to operate at high bandwidth despite using conventional noisy, coherent detectors. We demonstrate enhancement in shotnoise…
Remarkably, it has been shown that in principle, security proofs for quantum key-distribution (QKD) protocols can be independent of assumptions on the devices used and even of the fact that the adversary is limited by quantum theory. All…
Large Language Models (LLMs) are widely deployed in real-world systems. Given their broader applicability, prompt engineering has become an efficient tool for resource-scarce organizations to adopt LLMs for their own purposes. At the same…
Jailbreak attacks, where harmful prompts bypass generative models' built-in safety, raise serious concerns about model vulnerability. While many defense methods have been proposed, the trade-offs between safety and helpfulness, and their…
Backdoor attacks pose a serious threat to deep neural networks (DNNs), allowing adversaries to implant triggers for hidden behaviors in inference. Defending against such vulnerabilities is especially difficult in the post-training setting,…
We analyze the security of the two-way continuous-variable quantum key distribution protocol in reverse reconciliation against general two-mode attacks, which represent all accessible attacks at fixed channel parameters. Rather than against…
Data poisoning attacks and backdoor attacks aim to corrupt a machine learning classifier via modifying, adding, and/or removing some carefully selected training examples, such that the corrupted classifier makes incorrect predictions as the…
Even when prompts and parameters are secured, transformer language models remain vulnerable because their key-value (KV) cache during inference constitutes an overlooked attack surface. This paper introduces Malicious Token Injection (MTI),…
We propose an improved two-way continuous-variable quantum key distribution (CV QKD) protocol by adding proper random noise on the receiver's homodyne detection, the security of which is analysed against general collective attacks. The…
Quantum key distribution (QKD) can be used to generate secret keys between two distant parties. Even though QKD has been proven unconditionally secure against eavesdroppers with unlimited computation power, practical implementations of QKD…
We consider the security of continuous-variable quantum key distribution using thermal (or noisy) Gaussian resource states. Specifically, we analyze this against collective Gaussian attacks using direct and reverse reconciliation where both…
In this paper,we propose a modified Anshel-Anshel-Goldfeld(AAG) key exchange scheme. The hardness assumption underlying this modified construction is based on the membership problem for Mihailova subgroups of the braid group, a problem that…
Experimental Quantum Key Distribution (QKD) protocols have to consist of not only the unconditionally secure quantum transmission, but also a subsequent classical exchange that enables key reconciliation and error correction. There is a…
Quantum cryptographic protocols are typically analysed by assuming that potential opponents can carry out all physical operations, an assumption which grants capabilities far in excess of present technology. Adjusting this assumption to…
Quantum key distribution using weak coherent states and homodyne detection is a promising candidate for practical quantum-cryptographic implementations due to its compatibility with existing telecom equipment and high detection…
The security of neural cryptography is investigated. A key-exchange protocol over a public channel is studied where the parties exchanging secret messages use multilayer neural networks which are trained by their mutual output bits and…
The Kish key distribution system has been proposed as a class ical alternative to quantum key distribution. The idealized Kish scheme elegantly promise s secure key distribution by exploiting thermal noise in a transmission line. However,…
When large language model (LLM) systems interact with external data to perform complex tasks, a new attack, namely prompt injection, becomes a significant threat. By injecting instructions into the data accessed by the system, the attacker…
Multimodal Large Language Models (MLLMs) have achieved remarkable success in cross-modal understanding and generation, yet their deployment is threatened by critical safety vulnerabilities. While prior works have demonstrated the…
While ideal quantum key distribution (QKD) systems are well-understood, practical implementations face various vulnerabilities, such as side-channel attacks resulting from device imperfections. Current security proofs for decoy-state BB84…