两篇新研究论文探讨了机器学习模型的高级隐私技术。第一篇论文介绍了“鲁棒隐私”（RP），一种利用认证鲁棒性在推理过程中保护敏感属性的方法，显著降低了属性推断精度和模型反演攻击的成功率。第二篇论文提出了“气球均值”，一种计算上可行且鲁棒的差分隐私均值估计器，在污染数据设置下表现良好，并在模拟中优于现有方法。 AI
影响 这些论文为增强机器学习模型的隐私引入了新的理论框架和实用估计器，可能带来更安全的AI应用。
排序理由 两篇在arXiv上发表的学术论文，详细介绍了机器学习隐私的新颖方法。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2601.17360v2 Announce Type: replace-cross Abstract: An adversary observing a model's released prediction can infer sensitive attributes of the queried input, or even reconstruct representatives of the model's training data. The inference interface thus acts as a side channe…
arXiv:2606.12654v1 Announce Type: cross Abstract: We develop a new, differentially private mean estimator called the balloon mean. The main features of the balloon mean are that it is computationally tractable and enjoys robustness to outlying observations. It is based on an iter…
We develop a new, differentially private mean estimator called the balloon mean. The main features of the balloon mean are that it is computationally tractable and enjoys robustness to outlying observations. It is based on an iterative clipping procedure over expanding Mahalanobi…