A First Look At Efficient And Secure On-Device LLM Inference Against KV
Leakage

A First Look At Efficient And Secure On-Device LLM Inference Against KV Leakage

6 September 2024

Yuanchun Li

ArXiv (abs)PDF HTML

Papers citing "A First Look At Efficient And Secure On-Device LLM Inference Against KV Leakage"

8 / 8 papers shown

Title
TransLinkGuard: Safeguarding Transformer Models Against Model Stealing in Edge Deployment Qinfeng Li Zhiqiang Shen Zhenghan Qin Yangfan Xie Xuhong Zhang Tianyu Du Jianwei Yin 53 8 0 17 Apr 2024
LeftoverLocals: Listening to LLM Responses Through Leaked GPU Local Memory Tyler Sorensen Heidy Khlaaf 24 5 0 29 Jan 2024
Qwen Technical Report Jinze Bai Shuai Bai Yunfei Chu Zeyu Cui Kai Dang ... Zhenru Zhang Chang Zhou Jingren Zhou Xiaohuan Zhou Tianhang Zhu OSLM 266 1,908 0 28 Sep 2023
TenSEAL: A Library for Encrypted Tensor Operations Using Homomorphic Encryption Ayoub Benaissa Bilal Retiat Bogdan Cebere Alaa Eddine Belfedhal FedML 89 138 0 07 Apr 2021
DarkneTZ: Towards Model Privacy at the Edge using Trusted Execution Environments Fan Mo Ali Shahin Shamsabadi Kleomenis Katevas Soteris Demetriou Ilias Leontiadis Andrea Cavallaro Hamed Haddadi FedML 66 181 0 12 Apr 2020
A Survey of Techniques for Improving Security of GPUs Sparsh Mittal S. B. Abhinaya M. Reddy Irfan Ali 34 24 0 31 Mar 2018
MobileNetV2: Inverted Residuals and Linear Bottlenecks Mark Sandler Andrew G. Howard Menglong Zhu A. Zhmoginov Liang-Chieh Chen 209 19,335 0 13 Jan 2018
Very Deep Convolutional Networks for Large-Scale Image Recognition Karen Simonyan Andrew Zisserman FAtt MDE 1.7K 100,529 0 04 Sep 2014