3 papers
cs.CR2025
TZ-LLM: Protecting On-Device Large Language Models with Arm TrustZone
Xunjie Wang, Jiacheng Shi, Zihan Zhao +3
Large Language Models (LLMs) deployed on mobile devices offer benefits like user privacy and reduced network latency, but introduce a significant security risk: the leakage of prop…
cs.LG2025
Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs
Xun Wang, Jing Xu, Franziska Boenisch +3
Prompting has become a dominant paradigm for adapting large language models (LLMs). While discrete (textual) prompts are widely used for their interpretability, soft (parameter) pr…
cs.CV2025
Improving the Transferability of Adversarial Attacks by an Input Transpose
Qing Wan, Shilong Deng, Xun Wang
Deep neural networks (DNNs) are highly susceptible to adversarial examples--subtle perturbations applied to inputs that are often imperceptible to humans yet lead to incorrect mode…