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

Revisiting EM-based Estimation for Locally Differentially Private Protocols

Yutong Ye (Institute of software, Chinese Academy of Sciences & Zhongguancun Laboratory, Beijing, PR.China.), Tianhao Wang (University of Virginia), Min Zhang (Institute of Software, Chinese Academy of Sciences), Dengguo Feng (Institute of Software, Chinese Academy of Sciences)

Read More

Safety Misalignment Against Large Language Models

Yichen Gong (Tsinghua University), Delong Ran (Tsinghua University), Xinlei He (Hong Kong University of Science and Technology (Guangzhou)), Tianshuo Cong (Tsinghua University), Anyu Wang (Tsinghua University), Xiaoyun Wang (Tsinghua University)

Read More

ReThink: Reveal the Threat of Electromagnetic Interference on Power...

Fengchen Yang (Zhejiang University; ZJU QI-ANXIN IoT Security Joint Labratory), Zihao Dan (Zhejiang University; ZJU QI-ANXIN IoT Security Joint Labratory), Kaikai Pan (Zhejiang University; ZJU QI-ANXIN IoT Security Joint Labratory), Chen Yan (Zhejiang University; ZJU QI-ANXIN IoT Security Joint Labratory), Xiaoyu Ji (Zhejiang University; ZJU QI-ANXIN IoT Security Joint Labratory), Wenyuan Xu (Zhejiang University; ZJU…

Read More