研究人员开发了新的近似差分隐私“混合机制”，重点关注中低隐私设置。这些机制结合了多个高斯分布，与标准的解析高斯机制相比，提高了效率并降低了噪声。新方法显著缩小了低隐私场景下的最优性差距，并适用于各种统计推断任务，包括高维模型。 AI
影响 差分隐私的这些进展可以实现更强大、更私密的机器学习模型训练，尤其是在敏感数据应用中。
排序理由 该集群包含多篇 arXiv 预印本，详细介绍了差分隐私和变分推断方面的新研究。
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 4 个来源。 我们如何撰写摘要 →
We design a class of additive noise mechanisms that satisfy \((\varepsilon, δ)\)-differential privacy (DP) for scalar, real-valued query functions with known sensitivities, with a particular focus on moderate and low-privacy regimes. These mechanisms, which we call \textit{mixtur…
arXiv:2410.19371v3 Announce Type: replace Abstract: Differential privacy (DP) provides robust privacy guarantees for statistical inference, but this can lead to unreliable results and biases in downstream applications. While several noise-aware approaches have been proposed which…
arXiv:2605.28078v1 Announce Type: cross Abstract: We design a class of additive noise mechanisms that satisfy \((\varepsilon, \delta)\)-differential privacy (DP) for scalar, real-valued query functions with known sensitivities, with a particular focus on moderate and low-privacy …
We design a class of additive noise mechanisms that satisfy \((\varepsilon, δ)\)-differential privacy (DP) for scalar, real-valued query functions with known sensitivities, with a particular focus on moderate and low-privacy regimes. These mechanisms, which we call \textit{mixtur…