ResearchLatent Space

[AINews] How to steal a Reasoning Trace

#ai#security#vulnerability#privacy#reasoning

English

A recent paper reveals a vulnerability in frontier AI APIs that allows the extraction of hidden reasoning from models, matching billed API thinking tokens. This exposure has led to the discovery of sensitive data, including API keys and personal information, raising concerns about privacy and security in AI systems.

中文

最近的一篇论文揭示了前沿AI API中的一个漏洞，允许提取模型的隐藏推理，且与计费的API思维令牌相匹配。这一曝光导致发现了敏感数据，包括API密钥和个人信息，引发了对AI系统隐私和安全的担忧。