CASEBOOK

Browse / Sensitive Data Disclosure / AIID-357

GPT-2 Reportedly Reproduced Personal Data from Its Training Data

AIID-357 ยท 2019-02-14 real-world incident

Class
Sensitive Data Disclosure (filed by a model that read the source)
Technique
Real-world incidents
Affected
Openai (incident)

What happened, in short

GPT-2 memorized and reproduced personal data from its training set, including names, emails, social media handles and phone numbers. (Our summary, written by a model. The source text is below.)

Details

OpenAI's GPT-2 reportedly memorized and reproduced portions of its training data, including personal information such as names, email addresses, social media handles, and phone numbers. Researchers raised concerns that large language models could expose private or sensitive information when trained on web-scale datasets containing personal data.

References

Source: AI Incident Database, used under CC BY-SA 4.0.