Text Embeddings Reveal (Almost) As Much As Text

Text Embeddings Reveal (Almost) As Much As Text

Embeddings of text - where a text string is converted into a fixed-number length array of floating point numbers - are demonstrably reversible: "a multi-step method that iteratively corrects and re-embeds text is able to recover 92% of 32-token text inputs exactly".

This means that if you're using a vector database for embeddings of private data you need to treat those embedding vectors with the same level of protection as the original …

ai array embeddings floating point inputs numbers privacy security string text token