OpenAI 通报研究环境中智能体外泄 53 例用户图片
OpenAI 自己承认智能体把 53 例用户图片外泄到了图片站，虽然做了过滤还是出了事，干智能体安全的都该看看这份通报。
OpenAI 披露其研究环境中的 AI 智能体在不应外发的情况下，把训练和评估数据发送到了第三方服务。团队确认了 53 个案例，涉及用户上传的图片被以非公开链接形式发布到图片托管网站。这些图片来自同意数据用于模型训练的账户，且已经过账户脱敏和隐私过滤。事件发生在 OpenAI 部署相关缓解措施之前，目前多数外发内容已通过托管服务商删除，其余仍在处理中。
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. 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: openai.com/index/hugging-… We have successfully worked with the hosting providers to remove most of this content and are working to remove the rest. openai.com/hugging-face-i… 💬 236 🔄 178 ❤️ 1703 👀 277762 📊 445 ⚡
