OpenAI报告GPT-6 Astra越狱抵抗能力提升
OpenAI称,自动红队生成的越狱训练数据帮助训练GPT-6 Astra与Sol提高对网络、生物和暴力活动攻击的抵抗能力。在未启用生产安全防护的评估中,GPT-6 Astra安全回答了91.5%的固定网络越狱提示,而GPT-5.6 Sol为59%。OpenAI还称,在困难提示评估中,Astra比早期模型更少拒绝合法请求,并表示模型安全训练只是部署阶段更广泛防护体系的一环。
OpenAI的受控实验显示,在鲁棒化提示上进行强化学习与越狱抵抗能力提升相关,其中包括对自适应攻击者的测试。其困难提示评估还显示,Astra在更安全地处理有害请求的同时,减少了对合法请求的拒绝。
Frontier models are already very capable in high-stakes domains such as cyber and biology, helping security teams find and fix vulnerabilities in software and helping scientists uncover promising leads in disease research. As these capabilities advance, we work diligently to prevent misuse, and focus on adversarial robustness as an increasingly critical component of AI safety.
At OpenAI, we aim to empower everyone with frontier intelligence to make discoveries and build things. To reduce the risk of misuse, we deploy high-stakes capabilities through trusted access programs such as Daybreak for cybersecurity and Rosalind for biology, which grant vetted and trusted users access to these powerful capabilities.
A key technical challenge here is fuzzy robustness, a term we use to describe how reliably models withhold disallowed assistance under adversarial pressure, including jailbreaks. This is especially difficult in dual-use domains such as cyber and biology, where the same information can support beneficial or harmful work. We take a defense-in-depth approach at deployment, combining model safety training with additional safeguards. While we work to make each layer as robustly safe as possible, this blog post focuses only on the model layer.
#OpenAI#GPT-6 Astra#GPT-6 Sol#GPT-5.6 Sol#GPT-Red#Daybreak#Rosalind