We ran an experiment using Morris et. al’s Vec2Text model, to demonstrate the privacy risk of text embeddings with sensitive data. As we’ll show, a large percentage of sensitive data can be recovered from just their text embeddings, posing a significant privacy risk and demonstrating the need to use a tool like Tonic Textual to protect your data before using it to build generative AI systems.

The post Sensitive data in text embeddings is recoverable appeared first on Security Boulevard.

Expert Insights on Synthetic Data from the Tonic.ai Blog

Source: Security Boulevard
Source Link: https://securityboulevard.com/2025/07/sensitive-data-in-text-embeddings-is-recoverable/?utm_source=rss&utm_medium=rss&utm_campaign=sensitive-data-in-text-embeddings-is-recoverable