Researchers extract production ChatGPT training data at scale
Researchers used a divergence attack to make deployed ChatGPT emit memorized training data at 150 times its normal rate, extracting megabytes for about $200 and exposing personal information.
TOWARD DOOM58confidence 98/100
Why it moved the index
A practical low-cost attack extracted private memorized data from a deployed aligned model, directly demonstrating that alignment did not prevent scalable privacy compromise.
0 comments · 0 votes
Sign in to join the discussion →
No comments yet. Start the discussion.
AUDIT TRAIL
Assessment history
- R1Toward 58 · confidence 98
New November 2023 practical production-model data-extraction result.
12 Aug 2026