paper-with-me

홈 › Papers

Attacks on Third-Party APIs of Large Language Models

2024-04-24 · Wanru Zhao, Vidit Khazanchi, Haodi Xing, Xuanli He, Qiongkai Xu, Nicholas Donald Lane

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.

📄 PDF Abstract BibTeX arXiv:2404.16891

Code (1)

vk0812/third-party-attacks-on-llms 공식 구현

Tasks

Language ModelingLanguage ModellingLarge Language Model

Similar Papers 제목 키워드 기반

Adversarial Search Engine Optimization for Large Language Models

2024-06-26 · Fredrik Nestaas, Edoardo Debenedetti, Florian Tramèr

Large Language Models (LLMs) are increasingly used in applications where the model selects from competing third-party content, such as in LLM-powered search engines or chatbot plugins. In this paper, we introduce Prefere…

Chatbot

When AI Meets the Web: Prompt Injection Risks in Third-Party AI Chatbot Plugins

2025-11-08 · Yigitcan Kaya, Anton Landerer, Stijn Pletinckx, Michelle Zimmermann 외 arxiv

Prompt injection attacks pose a critical threat to large language models (LLMs), with prior work focusing on cutting-edge LLM applications like personal copilots. In contrast, simpler LLM applications, such as customer s…

Code Generation

CODESYNC: Synchronizing Large Language Models with Dynamic Code Evolution at Scale

2025-02-23 · Chenlong Wang, Zhaoyang Chu, Zhengxiang Cheng, Xuyi Yang 외

Large Language Models (LLMs) have exhibited exceptional performance in software engineering yet face challenges in adapting to continually evolving code knowledge, particularly regarding the frequent updates of third-par…

Chain-of-Scrutiny: Detecting Backdoor Attacks for Large Language Models

2024-06-10 · Xi Li, Ruofan Mao, Yusen Zhang, Renze Lou 외

Large Language Models (LLMs), especially those accessed via APIs, have demonstrated impressive capabilities across various domains. However, users without technical expertise often turn to (untrustworthy) third-party ser…

Prompt Engineering

MobiFlow: Real-World Mobile Agent Benchmarking through Trajectory Fusion

2026-02-28 · Yunfei Feng, Xi Zhao, Cheng Zhang, Dahu Feng 외 arxiv

Mobile agents can autonomously complete user-assigned tasks through GUI interactions. However, existing mainstream evaluation benchmarks, such as AndroidWorld, operate by connecting to a system-level Android emulator and…