Safety
Encoded but Exposed: Language Embeddings can Reveal More Than They Should in Recommender Systems
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 whethe
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.
Related
- The Best of the Two Worlds: Harmonizing Semantic and Hash IDs for Sequential Recommendation
- Value-Action Alignment in Large Language Models under Privacy-Prosocial Conflict
- An Empirical Study of Privacy Leakage Chains via Prompt Injection in Black-Box Chatbot Environments
Source: arXiv cs.AI | 2026-10-16