Attacks on Third-Party APIs of Large Language Models

TL;DR

This paper introduces a framework to identify security vulnerabilities in large language models that use third-party APIs, revealing real-world malicious attack scenarios and proposing strategies to enhance ecosystem safety.

Contribution

It presents a novel attacking framework specifically designed for LLMs with third-party API integrations, highlighting security risks and potential mitigation strategies.

Findings

Identified real-world malicious attacks on third-party APIs

Demonstrated how attacks can alter LLM outputs imperceptibly

Provided strategic recommendations for improving LLM ecosystem security

Abstract

Large language model (LLM) services have recently begun offering a plugin ecosystem to interact with third-party API services. This innovation enhances the capabilities of LLMs, but it also introduces risks, as these plugins developed by various third parties cannot be easily trusted. This paper proposes a new attacking framework to examine security and safety vulnerabilities within LLM platforms that incorporate third-party services. Applying our framework specifically to widely used LLMs, we identify real-world malicious attacks across various domains on third-party APIs that can imperceptibly modify LLM outputs. The paper discusses the unique challenges posed by third-party API integration and offers strategic possibilities to improve the security and safety of LLM ecosystems moving forward. Our code is released at https://github.com/vk0812/Third-Party-Attacks-on-LLMs.