绕过了 Stolen Thoughts 之后的缓解措施,说明推理蒸馏防护仍可被突破。
llm绕过报告
RT @xint_official: 🚨🚨 Xint researcher @tjbecker found a vulnerability that enabled large scale OpenAI model reasoning distillation that bypassed earlier mitigations set in place post-Stolen Thoughts. We disclosed responsibly to OpenAI and they completed patching last week. Full technical writeup here.
https://t.co/Z8Hsl4A7jX