OpenAI says it blocked distillation theft attack, but researchers say the same method can still steal reasoning content from models such as GPT-6 Astra on Azure
Original title:OpenAI says it stopped a campaign to steal its models' reasoning, but the trick still worked on Azure
AI summary
OpenAI said it blocked a distillation theft campaign targeting its model reasoning chains in July, with 16,000 requests from more than 4,000 users between July 24 and 25, linked to more than 15,000 accounts. OpenAI linked it to people associated with Moonshot AI and shut it down on July 28.
Key Takeaways
- OpenAI said it blocked a distillation theft campaign targeting its model reasoning chains in…
- 000 requests from more than 4,000 users between July 24 and 25,linked to more than 15,000 accounts.
- OpenAI linked it to people associated with Moonshot AI and shut it down on July 28.
Quick Facts
- Published
- Updated
- Source
- The Decoder:AI News(RSS)
- Category
- Industry
- AI score
- 77
原文把 OpenAI 的拦截行动与研究团队的复测放在一起看,读者可以了解同一模型在不同云平台防护不一致的问题。
Related entities
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
How to Cite
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: OpenAI says it blocked distillation theft attack, but researchers say the same method can still steal reasoning content from models such as GPT-6 Astra on Azure. October 1, 2026. https://new.nat6.net/en/news/uxe9v0hypn93df9ogn6glwled/