GPT-2 users

Incidents Harmed By

Incident 3573 Report
GPT-2 Reportedly Reproduced Personal Data from Its Training Data

2019-02-14

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.

Related Entities

OpenAI

Incidents involved as both Developer and Deployer

Incident 357
3 Reports
GPT-2 Reportedly Reproduced Personal Data from Its Training Data

People whose personal data was included in GPT-2 training data

Incidents Harmed By

Incident 357
3 Reports
GPT-2 Reportedly Reproduced Personal Data from Its Training Data

GPT-2

Incidents implicated systems

Incident 357
3 Reports
GPT-2 Reportedly Reproduced Personal Data from Its Training Data

Large language models

Incidents implicated systems

Incident 357
3 Reports
GPT-2 Reportedly Reproduced Personal Data from Its Training Data

Chatbots

Incidents implicated systems

Incident 357
3 Reports
GPT-2 Reportedly Reproduced Personal Data from Its Training Data