发现OpenRouter网关可能破坏提示缓存隔离，导致用户间数据泄露风险。
CacheProbe: Auditing Prompt Cache Isolation in Gateway APIs
- 通过时序攻击检测OpenRouter网关是否存在跨用户缓存共享漏洞。
- 实验证明共享组织凭证下缓存可被多个用户访问，突破了账户级隔离。
- 揭示API网关架构中隐含的安全风险，适合关注LLM安全的开发者参考。
过去一年，大型语言模型（LLMs）的推理API中提示缓存越来越普及。提示缓存通过复用特定提示的键值（KV）缓存来节省计算资源并加速响应。然而，许多实现对时序攻击或基本元数据泄露缺乏防御能力。Gu等（ICML 2025）提出了一种审计提示缓存的方法。本文研究OpenRouter的API网关架构是否引入提示缓存漏洞，从而绕过提供商级别的提示缓存隔离保证。多数LLM推理提供商采用按账户或按组织的提示缓存机制以防止数据泄露，但通过OpenRouter使用共享组织凭证，是否会无意中在所有OpenRouter用户之间创建全局缓存共享？实验表明，这种架构确实存在跨用户缓存访问风险。
原文摘要 · Abstract (English)
Over the past year, prompt caching in Large Language Models (LLMs) has become increasingly more popular across inference APIs. Prompt caching helps save precious compute resources and speeds up response times by reusing parts of the KV cache of a specific prompt for another request. However, many implementations of prompt caching are not secure against timing attacks or even basic metadata disclosure. Gu et al. (ICML 2025) develop a method to audit prompt caching in LLMs. This paper investigates whether OpenRouter's API gateway architecture introduces prompt caching vulnerabilities that bypass provider-level prompt cache isolation guarantees. Most LLM inference providers implement per-account or per-organization prompt caching to prevent data leaks, but does routing through OpenRouter with shared organizational credentials inadvertently create global cache sharing across all OpenRouter users?
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。