Guanlong Wu (Southern University of Science and Technology), Zheng Zhang (ByteDance Inc.), Yao Zhang (ByteDance Inc.), Weili Wang (Southern University of Science and Technolog), Jianyu Niu (Southern University of Science and Technolog), Ye Wu (ByteDance Inc.), Yinqian Zhang (Southern University of Science and Technology (SUSTech))

Large Language Models (LLMs), which laid the groundwork for Artificial General Intelligence (AGI), have recently gained significant traction in academia and industry due to their disruptive applications. In order to enable scalable applications and efficient resource management, various multi-tenant LLM serving frameworks have been proposed, in which the LLM caters to the needs of multiple users simultaneously. One notable mechanism in recent works, such as SGLang and vLLM, is sharing the Key-Value (KV) cache for identical token sequences among multiple users, saving both memory and computation. This paper presents the first investigation on security risks
associated with multi-tenant LLM serving. We show that the state-of-the-art mechanisms of KV cache sharing may lead to new side channel attack vectors, allowing unauthorized reconstruction
of user prompts and compromising sensitive user information among mutually distrustful users. Specifically, we introduce our attack, PROMPTPEEK, and apply it to three scenarios where the
adversary, with varying degrees of prior knowledge, is capable of reverse-engineering prompts from other users. This study underscores the need for careful resource management in multi-tenant LLM serving and provides critical insights for future security enhancement.

View More Papers

BrowserFM: A Feature Model-based Approach to Browser Fingerprint Analysis

Maxime Huyghe (Univ. Lille, Inria, CNRS, UMR 9189 CRIStAL), Clément Quinton (Univ. Lille, Inria, CNRS, UMR 9189 CRIStAL), Walter Rudametkin (Univ. Rennes, Inria, CNRS, UMR 6074 IRISA)

Read More

Inspecting Compiler Optimizations on Mixed Boolean Arithmetic Obfuscation

Rachael Little, Dongpeng Xu (University of New Hampshire)

Read More

The (Un)usual Suspects – Studying Reasons for Lacking Updates...

Maria Hellenthal (CISPA Helmholtz Center for Information Security), Lena Gotsche (CISPA Helmholtz Center for Information Security), Rafael Mrowczynski (CISPA Helmholtz Center for Information Security), Sarah Kugel (Saarland University), Michael Schilling (CISPA Helmholtz Center for Information Security), Ben Stock (CISPA Helmholtz Center for Information Security)

Read More

DShield: Defending against Backdoor Attacks on Graph Neural Networks...

Hao Yu (National University of Defense Technology), Chuan Ma (Chongqing University), Xinhang Wan (National University of Defense Technology), Jun Wang (National University of Defense Technology), Tao Xiang (Chongqing University), Meng Shen (Beijing Institute of Technology, Beijing, China), Xinwang Liu (National University of Defense Technology)

Read More