Researchers Translate Embeddings Between AI Models Without Any Paired Data
Harnessing the Universal Geometry of Embeddings
A new paper from Cornell Tech introduces the first method to translate text embeddings between different vector spaces without paired data, encoders, or predefined matches. The unsupervised approach maps embeddings to and from a universal latent representation, achieving high cosine similarity across models with different architectures, parameter counts, and training data. This capability has serious security implications: an adversary with only embedding vectors could extract sensitive information from underlying documents, enabling classification and attribute inference.
An adversary with access only to embedding vectors can extract sensitive information about the underlying documents, sufficient for classification and attribute inference.