Related papers: Current injection and voltage insertion attacks ag…
For Transformer models, cryptographically secure inference ensures that the client learns only the final output, while the server learns nothing about the client's input. However, securely computing nonlinear layers remains a major…
Backdoor (trojan) attacks embed hidden, controllable behaviors into machine-learning models so that models behave normally on benign inputs but produce attacker-chosen outputs when a trigger is present. This survey reviews the rapidly…
The imperfections of a receiver's detector affect the performance of two-way continuous-variable quantum key distribution protocols and are difficult to adjust in practical situations. We propose a method to improve the performance of…
Quantum key distribution (QKD) based on the fundamental laws of quantum physics can allow the distribution of secure keys between distant users. However, the imperfections in realistic devices may lead to potential security risks, which…
The rapid advancement and widespread adoption of generative artificial intelligence (GenAI) and large language models (LLMs) has been accompanied by the emergence of new security vulnerabilities and challenges, such as jailbreaking and…
Recent generative engine optimisation (GEO) research has shown that prompt-injection attacks can push a target product to the top of an LLM's recommendation list, with the strongest attacks reporting around $80\%$ success and raising…
Defenses against security threats have been an interest of recent studies. Recent works have shown that it is not difficult to attack a natural language processing (NLP) model while defending against them is still a cat-mouse game. Backdoor…
Large Vision Language Models (LVLMs) demonstrate strong capabilities in multimodal reasoning and many real-world applications, such as visual question answering. However, LVLMs are highly vulnerable to jailbreaking attacks. This paper…
Graph neural network (GNN) have demonstrated exceptional performance in solving critical problems across diverse domains yet remain susceptible to backdoor attacks. Existing studies on backdoor attack for graph classification are limited to…
In recent years, discrete-modulated continuous-variable quantum key distribution (DM-CV-QKD) has gained traction due to its practical advantages: cost-effectiveness, simple state preparation, and compatibility with existing communication…
Security alignment enables the Large Language Model (LLM) to gain the protection against malicious queries, but various jailbreak attack methods reveal the vulnerability of this security mechanism. Previous studies have isolated LLM…
This paper studies a multiple-input multiple-output (MIMO) free-space optical (FSO) communication system employing continuous-variable quantum key distribution (CV-QKD), with the goal to support secret key transmission between two…
Large Audio-Language Models (LALMs) are increasingly deployed in real-world applications, yet their robustness against malicious audio injection attacks remains underexplored. This study systematically evaluates five leading LALMs across…
Backdoor attack intends to embed hidden backdoor into deep neural networks (DNNs), such that the attacked model performs well on benign samples, whereas its prediction will be maliciously changed if the hidden backdoor is activated by the…
Security of a continuous-variable quantum key distribution protocol based on noisy coherent states and channel is analyzed. Assuming the noise of coherent states is induced by Fred, a neutral party relative to others, we prove that the…
Logic locking has emerged as a prominent key-driven technique to protect the integrity of integrated circuits. However, novel machine-learning-based attacks have recently been introduced to challenge the security foundations of locking…
The fabrication of quantum key distribution (QKD) systems typically involves several parties, thus providing Eve with multiple opportunities to meddle with the devices. As a consequence, conventional hardware and/or software hacking attacks…
This paper investigates the security issue of the data replay attacks on the control systems. The attacker is assumed to interfere with the control system process in a steady-state case. The problem is presented as the standard way to…
Li et al. presented a protocol [Int. Journal of Quantum Information, Vol. 4, No. 6 (2006) 899-906] for quantum key distribution based on entanglement swapping. In this protocol they use random and certain bits to construct a classical key…
Establishing scalable, secure quantum networks requires advancing beyond conventional point-to-point quantum key distribution (QKD) protocols toward point-to-multipoint QKD protocols. Here, we generalize a well-established…