arXiv cs.AI· Linda Bekov\'a, Rodrigo Alves·· 2 天前AI 评分31
语言嵌入在推荐系统中可能泄露超出预期的物品信息
Encoded but Exposed: Language Embeddings can Reveal More Than They Should in Recommender Systems
AI 导读
研究发现，当攻击者掌握外部来源的辅助物品文本时，一个简单的余弦相似度攻击即可在多个语言模型和候选集设置下以高平均倒数排名恢复物品身份，两个真实数据集上均验证了该泄露。物品泄露还可从稀疏评分进一步传播为用户重识别，而混淆描述虽能缓解泄露，却存在明显的泄露-效用权衡。
正文 · 原文
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.
| Subjects: | Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.21713 [cs.CR] |
| (or arXiv:2610.21713v1 [cs.CR] for this version) | |
| https://doi.org/10.48550/arXiv.2610.21713 arXiv-issued DOI via DataCite (pending registration) |
|
| Journal reference: | 3rd Workshop on Evaluating and Applying Recommender Systems with Large Language Models (EARL 2026), co-located with the 35th ACM International Conference on Information and Knowledge Management (CIKM 2026) |
Submission history
From: Rodrigo Alves [view email]
[v1]
Thu, 15 Oct 2026 11:32:41 UTC (45 KB)
来源：arXiv cs.AI · arxiv.org