2026-10-16 · ArXiv
arXiv:2610.21713v1 Announce Type: cross
Abstract: Language embeddings are increasingly used in recommenders to represent item content, but their privacy risks remain poorly understood. We study whether item embeddings can reveal item identities when an adversary has access to auxiliary item text from external sources. We show that a simple cosine-similarity attack can recover item identities with high mean reciprocal rank across language models and candidate-set settings on two real-world datasets. Leakage is strongest when the adversary's partial information overlaps with the victim representation, but it also persists through semantic alignment between independently sourced descriptions. We further show that item leakage can propagate to user re-identification from sparse ratings. Finally, we evaluate obfuscated descriptions as a mitigation and find a clear leakage-utility tradeoff.
原文链接：https://arxiv.org/abs/2610.21713
查看更多资讯请见 AI 行业资讯。