Yuhao Wu (Washington University in St. Louis), Franziska Roesner (University of Washington), Tadayoshi Kohno (University of Washington), Ning Zhang (Washington University in St. Louis), Umar Iqbal (Washington University in St. Louis)

Large language models (LLMs) extended as systems, such as ChatGPT, have begun supporting third-party applications. These LLM apps leverage the de facto natural language-based automated execution paradigm of LLMs: that is, apps and their interactions are defined in natural language, provided access to user data, and allowed to freely interact with each other and the system. These LLM app ecosystems resemble the settings of earlier computing platforms, where there was insufficient isolation between apps and the system. Because third-party apps may not be trustworthy, and exacerbated by the imprecision of natural language interfaces, the current designs pose security and privacy risks for users. In this paper, we evaluate whether these issues can be addressed through execution isolation and what that isolation might look like in the context of LLM-based systems, where there are arbitrary natural language-based interactions between system components, between LLM and apps, and between apps. To that end, we propose IsolateGPT, a design architecture that demonstrates the feasibility of execution isolation and provides a blueprint for implementing isolation, in LLM-based systems. We evaluate IsolateGPT against a number of attacks and demonstrate that it protects against many security, privacy, and safety issues that exist in non-isolated LLM-based systems, without any loss of functionality. The performance overhead incurred by IsolateGPT to improve security is under 30% for three-quarters of tested queries.

View More Papers

Do We Really Need to Design New Byzantine-robust Aggregation...

Minghong Fang (University of Louisville), Seyedsina Nabavirazavi (Florida International University), Zhuqing Liu (University of North Texas), Wei Sun (Wichita State University), Sundararaja Iyengar (Florida International University), Haibo Yang (Rochester Institute of Technology)

Read More

mmProcess: Phase-Based Speech Reconstruction from mmWave Radar

Hyeongjun Choi, Young Eun Kwon, Ji Won Yoon (Korea University)

Read More

Towards Understanding Unsafe Video Generation

Yan Pang (University of Virginia), Aiping Xiong (Penn State University), Yang Zhang (CISPA Helmholtz Center for Information Security), Tianhao Wang (University of Virginia)

Read More

”Who is Trying to Access My Account?” Exploring User...

Tongxin Wei (Nankai University), Ding Wang (Nankai University), Yutong Li (Nankai University), Yuehuan Wang (Nankai University)

Read More