0 / 0
Exposing personal information risk for AI
Last updated: Dec 12, 2024
Exposing personal information risk for AI
Privacy Icon representing privacy risks.
Risks associated with output
Privacy
Amplified by generative AI

Description

When personal identifiable information (PII) or sensitive personal information (SPI) are used in training data, fine-tuning data, or as part of the prompt, models might reveal that data in the generated output. Revealing personal information is a type of data leakage.

Why is exposing personal information a concern for foundation models?

Sharing people’s PI impacts their rights and make them more vulnerable.

Background image for risks associated with input
Example

Exposure of personal information

Per the source article, ChatGPT suffered a bug and exposed titles and active users' chat history to other users. Later, OpenAI shared that even more private data from a small number of users was exposed including, active user’s first and last name, email address, payment address, the last four digits of their credit card number, and credit card expiration date. In addition, it was reported that the payment-related information of 1.2% of ChatGPT Plus subscribers were also exposed in the outage.

Parent topic: AI risk atlas

We provide examples covered by the press to help explain many of the foundation models' risks. Many of these events covered by the press are either still evolving or have been resolved, and referencing them can help the reader understand the potential risks and work towards mitigations. Highlighting these examples are for illustrative purposes only.

Generative AI search and answer
These answers are generated by a large language model in watsonx.ai based on content from the product documentation. Learn more