研究者称仍可通过第三方 API 从 Astra/Sol-6.1 提取推理内容
AI 导读
作者在推理提取攻击发布两个月后审计了厂商随后引入的缓解措施，发现仍能通过第三方 API 提供商从 Astra/Sol-6.1 中提取推理内容，并已将发现披露给 OpenAI 和 Anthropic。作者表示，企业需要覆盖的攻击面之大令人意外，攻击仍可能绕过防护；目前 Astra/Sol-6.1 的推理轨迹已对公众开放，作者也因此认为思维链监控可能相当困难。
正文
It was interesting to see how much attack surface exists for companies to cover and how we could still slip through with our attacks.
We now have Astra/Sol-6.1 traces for the public. I now see why CoT monitoring might be rough!
Two months after our reasoning extraction attack release, we audited mitigations introduced since then and found that we still can extract reasoning from Astra/Sol-6.1 via third-party API providers.
We disclosed our findings to OpenAI and Anthropic...
https://openai.com/index/disrupting-a-coordinated-model-distillation-campaign/在 X 查看被引用的帖子