跳到正文

How OpenAI Is Combating Adversarial Distillation

OpenAI News当事人·· 19 小时前精选Combatting adversarial distillation
打开原文
原文

中文版本尚未就绪 · 显示原文

图片来自 OpenAI News

发生了什么

OpenAI details its defenses against attempts to extract protected reasoning and use it to train models without comparable safeguards. In an internal adaptive black-box evaluation aggregated across six attacker models, the average success rate for extracting reasoning from an earlier request fell from 54.0% on GPT-6 Astra with original safeguards to 0.2% on GPT-6.2 Astra with updated safeguards. OpenAI also describes request-level protections, campaign investigations, and enforcement.

推荐理由

GPT-6.2 Astra reduced the average success rate for extracting protected reasoning from an earlier request to 0.2%, from 54.0% on GPT-6 Astra; the comparison comes from an internal adaptive black-box evaluation aggregated across six attacker models.

2 家信源报道

    接下来读什么

    查看这件事的完整进展OpenAI Details Defenses Against Adversarial Distillation
    这条收录于 11月21日 AI 日报看这一期日报的全部内容