Incident 357: GPT-2 Able to Recite PII in Training Data

Description: OpenAI's GPT-2 reportedly memorized and could regurgitate verbatim instances of training data, including personally identifiable information such as names, emails, twitter handles, and phone numbers.


New ReportNew ReportNew ResponseNew ResponseDiscoverDiscoverView HistoryView History
Alleged: OpenAI developed and deployed an AI system, which harmed OpenAI and people having personal data in GPT-2's training data.

Incident Stats

Incident ID
Report Count
Incident Date
Khoa Lam
Extracting Training Data from Large Language Models · 2020

It has become common to publish large (billion parameter) language models that have been trained on private datasets. This paper demonstrates that in such settings, an adversary can perform a training data extraction attack to recover indiv…

Does GPT-2 Know Your Phone Number? · 2020

Most likely not.

Yet, OpenAI’s GPT-2 language model does know how to reach a certain Peter W--- (name redacted for privacy). When prompted with a short snippet of Internet text, the model accurately generates Peter’s contact information, in…

What happens when your massive text-generating neural net starts spitting out people's phone numbers? If you're OpenAI, you create a filter · 2021

Special report OpenAI is building a content filter to prevent GPT-3, its latest and largest text-generating neural network, from inadvertently revealing people's personal information as it prepares to commercialize the software through an A…


A "variant" is an incident that shares the same causative factors, produces similar harms, and involves the same intelligent systems as a known AI incident. Rather than index variants as entirely separate incidents, we list variations of incidents under the first similar incident submitted to the database. Unlike other submission types to the incident database, variants are not required to have reporting in evidence external to the Incident Database. Learn more from the research paper.

Similar Incidents

By textual similarity

Did our AI mess up? Flag the unrelated incidents