0 / 0
Reidentification risk for AI
Last updated: Dec 12, 2024
Reidentification risk for AI
Privacy Icon representing privacy risks.
Risks associated with input
Training and tuning phase
Privacy
Traditional AI risk

Description

Even with the removal or personal identifiable information (PII) and sensitive personal information (SPI) from data, it might be possible to identify persons due to correlations to other features available in the data.

Why is reidentification a concern for foundation models?

Including irrelevant but highly correlated features to personal information for model training can increase the risk of reidentification.

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