两篇新研究论文探讨了差分隐私的进展。一篇论文表明，差分隐私文本重写在保留语义内容的同时，显著改变了文本的风格和交流特征，导致话语更加同质化。另一篇论文介绍了一种结合元学习和定向差分隐私的方法，通过选择性地扰动用户数据和增强模型鲁棒性，来改善推荐系统中准确性-隐私的权衡。 AI
影响 这些论文推进了语言模型和推荐系统的隐私保护技术，可能实现更安全的AI应用。
排序理由 两篇在arXiv上发表的学术论文，详细介绍了差分隐私技术的新研究。
AI 生成摘要 · Google Gemini · 来自 5 个来源。 我们如何撰写摘要 →
arXiv:2604.26656v1 Announce Type: new Abstract: Differential Privacy (DP) for text matured from disjointed word-level substitutions to contiguous sentence-level rewriting by leveraging the generative capacity of language models. While this form of text privatization is best suite…
arXiv:2604.26390v1 Announce Type: cross Abstract: Balancing differential privacy (DP) with recommendation accuracy is a key challenge in privacy-preserving recommender systems, since DP-noise degrades accuracy. We address this trade-off at both the data and model levels. At the d…
Differential Privacy (DP) for text matured from disjointed word-level substitutions to contiguous sentence-level rewriting by leveraging the generative capacity of language models. While this form of text privatization is best suited for balancing formal privacy guarantees with g…
Differential Privacy (DP) for text matured from disjointed word-level substitutions to contiguous sentence-level rewriting by leveraging the generative capacity of language models. While this form of text privatization is best suited for balancing formal privacy guarantees with g…
Balancing differential privacy (DP) with recommendation accuracy is a key challenge in privacy-preserving recommender systems, since DP-noise degrades accuracy. We address this trade-off at both the data and model levels. At the data level, we apply DP only to the most stereotypi…