GPT-5.5 生物漏洞赏金计划
阅读原文· openai.comOpenAI 将 GPT-5.5 Bio Bug Bounty 升级为持续私密项目 OpenAI Bio Bounty Program，以 GPT-5.6 为起点并覆盖后续前沿模型，旨在发现能突破预设生物安全挑战的通用越狱攻击。奖励从 $25,000 提高至 $50,000，适用于
OpenAI Bio Bug Bounty | OpenAI
July 9, 2026
OpenAI Bio Bug Bounty
Testing for universal jailbreaks for biorisks
Invitation
As part of our ongoing efforts to strengthen our safeguards for advanced AI capabilities in biology, we’re evolving our GPT‑5.5 Bio Bug Bounty to become an ongoing private program—the OpenAI Bio Bounty Program. The program will remain focused on universal jailbreaks that can defeat our predefined biosafety challenge against OpenAI’s frontier models, starting with GPT‑5.6 and going forward.
We’re also excited to announce that we’re increasing reward amounts. The reward for a universal jailbreak for the OpenAI Bio Bounty Program has been raised from $25,000 to $50,000 for both GPT‑5.6 and GPT‑5.5. Smaller awards may be granted for partial wins at our discretion.
We will continue to honor the scope for the GPT‑5.5 Bio Bounty Program as originally announced, with testing ending on July 27, 2026. After this date, only GPT‑5.6 will be in scope; we will continue to communicate any future changes in scope to our researchers.
Interested applicants should apply through our rolling application process . Once selected, accepted applicants will be onboarded to the bio bug bounty platform. All past applicants to the GPT‑5.5 Bio Bounty Program will not need to reapply.
How to participate
Submit a short application here (name, affiliation, experience). Accepted applicants must have existing ChatGPT accounts to apply, and will sign a NDA. Apply now and help us make frontier AI safer.
If you’re interested in supporting OpenAI’s work to deliver safe and secure artificial intelligence beyond the Bio Bounty program, you can learn about our Safety Bug Bounty and Security Bug Bounty programs.