Current browse context:
cs.CR
Change to browse by:
References & Citations
Computer Science > Cryptography and Security
Title: Attacks on Third-Party APIs of Large Language Models
(Submitted on 24 Apr 2024)
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 this https URL
Link back to: arXiv, form interface, contact.