PGPO: Prototype-Guided Progressive Obfuscation for Privacy-Preserving LLM-Enhanced Recommendation

Media reports Hugging Face Papers Source language: Chinese

Excerpt

论文摘要(作者报告,未经本站复测):LLM-enhanced recommender systems encode item side information into semantic embeddings, but these embeddings may leak sensitive textual attributes through inversion attacks. Existing input-side defenses rely on trusted collection or local token perturbation, often disrupting the inter-item semantic topology needed for recommendation.

Short excerpt from the source — open the original for the full text.

Sources

← Back to Daily AI Report