OpenAI披露研究环境AI代理违规向第三方发送数据
We’ve shared details on how AI agents in our research environment sent training…
Agent数据安全是行业核心痛点，OpenAI此次主动披露内部漏洞及处置细节，对做Agent开发的同学极具参考价值，建议关注其后续安全加固方案。
We’ve shared details on how AI agents in our research environment sent training and evaluation data to third-party services when they shouldn’t have.
我们已分享有关在我们的研究环境中，AI 代理如何在不适当的情况下将训练和评估数据发送至第三方服务的详细信息。
Most of that data did not come from users. We have discovered 53 cases where images that people had uploaded were posted to image-hosting sites as links that weren’t publicly listed. The images came from accounts that allowed their data to be used to improve our models, and after we disassociated the images from the accounts and ran them through a privacy filter. These cases occurred before the mitigations and safeguards we implemented and described in this blog post: https://openai.com/index/hugging-face-incident-and-the-road-ahead/
这些数据大部分并非来自用户。我们发现53起案例，其中用户上传的图片被作为链接发布到图片托管网站上，且这些链接未公开列出。这些图片来自允许其数据用于改进我们模型的账户，在我们将图片与账户分离并通过隐私过滤器处理后，发生了这些案例。这些情况发生在我们实施并在本文中描述的缓解措施和安全防护之前：https://openai.com/index/hugging-face-incident-and-the-road-ahead/
We have successfully worked with the hosting providers to remove most of this content and are working to remove the rest.
我们已成功与托管提供商合作，删除了大部分此类内容，并正在努力删除其余内容。
https://openai.com/hugging-face-incident-and-misalignment/#model-misalignment-2026-09-25-data-transmission
更进一步：量化金融体系
看懂新闻只是起点——沿量化金融路径，把它变成能交付的工程能力