Misuse and incidents

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.

CURRENT ASSESSMENT · REVISION 1
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 votesOpen discussion

Public discussion is readable by everyone. Sign in to comment, reply, or vote.

No comments yet. Start the discussion.

AUDIT TRAIL

Assessment history

  1. R1
    Toward 58 · confidence 98

    New November 2023 practical production-model data-extraction result.

    12 Aug 2026