The Decoder· Maximilian Schreiner·· 4 小时前AI 评分71
OpenAI 称已阻止推理内容窃取行动,但研究团队曾在 Azure 复现攻击
OpenAI says it stopped a campaign to steal its models' reasoning, but the trick still worked on Azure
AI 导读
OpenAI 称已封禁关联推理内容提取活动的逾 15,000 个账号并修补漏洞,但研究团队随后仍在 Azure 成功提取模型的隐藏推理。
来源:The Decoder · the-decoder.com