OpenAI 推出了 GPT-Red，一个内部自动化系统，旨在大规模识别其 AI 模型中的提示注入漏洞。该系统通过对抗性自我博弈进行学习，在此过程中它会尝试利用防御模型，并利用成功的攻击来改进未来的模型。OpenAI 报告称，针对 GPT-Red 的训练已使其 GPT-5.6 Sol 模型具有显著的更强韧性，在面对提示注入攻击时，其故障率比之前的生产模型低六倍。 AI
影响 增强了 AI 模型的安全性和韧性，有可能加速更强大的 AI 系统的开发和部署。
排序理由 OpenAI 宣布了一个新的内部系统 (GPT-Red)，用于提高 AI 模型的安全性和韧性，直接影响未来的模型开发。
AI 生成摘要 · Google Gemini · 来自 6 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
AI agents are already being used to improve the capabilities of our next-generation models. We believe with GPT-Red that we have started to unlock a similar flywheel for safety, where today's models can be used to make tomorrow's models more robust, aligned, and trustworthy.
Training against GPT‑Red makes GPT‑5.6 substantially more resilient. To measure this, we replayed some of GPT‑Red’s strongest attacks—none of which our models had seen during training. GPT‑5.6 Sol proved to be our most robust model against prompt injections to date, with 6× fewer
GPT‑Red learns through adversarial self-play, where its goal is to prompt inject a variety of challenging defender models. Every successful attack that GPT-Red finds is used to improve these defenders, pushing GPT‑Red to continuously find broader and more complex failures.
Introducing GPT-Red An internal automated red teamer on a mission to find our models’ prompt injection vulnerabilities at scale, helping us build stronger defenses before wider deployment. https://t.co/GxnmxxcpSk
As model capabilities grow, safety and alignment must scale with them. Red-teaming is essential, but today’s approaches are difficult to scale, creating a critical bottleneck. GPT‑Red is one way we’re addressing it.
# GPTRed , an # automatedredteaming model, was trained to discover # vulnerabilities in # AI models. By using GPT-Red to adversarially train GPT-5.6, the model became significantly more robust to # promptinjection attacks. This approach, combined with human and third-party red-te…