OpenAI Disrupts Reasoning Extraction Campaign Linked to Moonshot AI Associates
Summary: OpenAI said it identified and disrupted a coordinated distillation campaign to extract protected reasoning from its models, with a core cluster of activity traced to individuals associated with Beijing-based Moonshot AI. The activity began July 1, 2026, spiked on July 24 and 25 to 16,000 attempted requests from over 4,000 users, expanded to prompt-pattern activity across more than 15,000 users, and was fully disrupted on July 28, 2026.
Bottom line: OpenAI says the operators never broke encryption or touched a database - they manipulated model interactions at scale, and extracted reasoning can train another model without carrying over the original's safeguards. Moonshot AI was also accused by Anthropic last month of relaying customer requests to Claude and retaining exchanges to train its chain-of-thought model.
Read the original at The Hacker News ↗
- Topics
- AI Security
- Related
- SECURITY AFFAIRS AI-CYBERSECURITY NEWSLETTER ROUND 8 Cyber Risks · Nov 15, 2026Pentagon Renames CDAO ‘Super Intelligence Office’ Cyber Risks · Nov 15, 2026186 Fake AI Domains Redirect Users to Click Fix Lures, Browser Malware, and Search Hijackers Cyber Risks · Nov 12, 2026