Measuring Re-identification Risk. (arXiv:2304.07210v1 [cs.CR])

Compact user representations (such as embeddings) form the backbone of
personalization services. In this work, we present a new theoretical framework
to measure re-identification risk in such user representations. Our framework,
based on hypothesis testing, formally bounds the probability that an attacker
may be able to obtain the identity of a user from their representation. As an
application, we show how our framework is general enough to model important
real-world applications such as the Chrome's Topics API for interest-based
advertising. …

advertising algorithms api application applications arxiv chrome embeddings framework general good hypothesis identification identity personalization probability representation risk services testing topics work world