OpenAI 称已阻止推理窃取活动，但 Azure 上攻击仍有效
原标题：OpenAI says it stopped a campaign to steal its models' reasoning, but the trick still worked on Azure
AI 摘要
OpenAI 称其发现并关闭了一场针对模型隐藏推理过程的“对抗性蒸馏”攻击活动，该活动在7月24-25日达到峰值，涉及超1.5万个关联账户，并于7月28日前被完全封禁。OpenAI 将核心参与者与 Moonshot AI 相关人员关联。但研究人员指出，同类攻击在微软 Azure 上对 OpenAI 和 Anthropic 的模型仍然有效，包括新发布的 GPT-6 Astra，暴露出云平台防护不一致的问题。
正文节选
OpenAI says it stopped a campaign to steal its models' reasoning, but the trick still worked on Azure OpenAI says it has broken up a coordinated campaign to copy the hidden reasoning behind its AI models. Researchers found that the same trick kept working for weeks on cloud platforms like Microsoft Azure. In a blog post, OpenAI says it detected and shut down what's known as an "adversarial distillation" campaign. The attackers targeted the models' protected reasoning, meaning the internal steps