Attacks on Third-Party APIs of Large Language Models

2024/04/24 by Zhao, Wanru, Khazanchi, Vidit, Xing, Haodi +3 · 1 citation
#Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Computers and Society (cs.CY) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.2404.16891

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.

Cited by

• Memorization in Large Language Models in Medicine: Prevalence, Characteristics, and Implications

Related

• A Survey of Attacks on Large Language Models
• Chain-of-Scrutiny: Detecting Backdoor Attacks for Large Language Models
• LLM Platform Security: Applying a Systematic Evaluation Framework to OpenAI's ChatGPT Plugins
• Identifying and Mitigating Vulnerabilities in LLM-Integrated Applications
• Prompt Injection attack against LLM-integrated Applications