Towards Sharper Utility Bounds for Differentially Private Pairwise Learning
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络空间安全学院）；Renmin University of China（中国人民大学）
Pairwise learning focuses on learning tasks with pairwise loss functions, depends on pairs of training instances, and naturally fits for modeling relationships between pairs of samples. In this paper, we focus on the privacy of pairwise learning and propose a new differential privacy paradigm for pairwise learning, based on gradient perturbation. Except for the privacy guarantees, we also analyze the excess population risk and give corresponding bounds under both expectation and high probability conditions. We use the \textit{on-average stability} and the \textit{pairwise locally elastic stability} theories to analyze the expectation bound and the high probability bound, respectively. Moreover, our analyzed utility bounds do not require convex pairwise loss functions, which means that our method is general to both convex and non-convex conditions. Under these circumstances, the utility bounds are similar to (or better than) previous bounds under convexity or strongly convexity assumption, which are attractive results.
University of Michigan（密歇根大学）；University of Pennsylvania（宾夕法尼亚大学）；Google Research（谷歌研究院）
能够高效准确地选择具有差分隐私的顶级$k$元素是各种隐私数据分析任务的组成部分。在本文中，我们提出了oneshot拉普拉斯机制，它概括了著名的报告噪声最大的机制，以报告嘈杂的顶部$k$元素。我们发现，oneshot拉普拉斯机制的噪音水平为$\widetilde{O}(\sqrt{k}/\eps)$近似差分私人。与之前运行Report Noisy Max $k$次的剥离方法相比，oneshot Laplace机制仅添加噪声并计算顶部$k$元素一次，因此对于大型$k$更有效。此外，我们的隐私证明依赖于一种新的耦合技术，绕过使用的组合定理。最后，我们提出了一个新的应用程序，有效的顶部$k$选择的经典问题，从成对比较排名。
DP-FedPGN: Finding Global Flat Minima for Differentially Private Federated Learning via Penalizing Gradient Norm
School of Computer Science and Technology, College of Intelligence and Computing, Tianjin University（计算机科学与技术学院，智能与计算学院，天津大学）；Medical College, Tianjin University（医学学院，天津大学）；School of Artificial Intelligence, Xidian University（人工智能学院，西安电子科技大学）
Differentially Private Preference Data Synthesis for Large Language Model Alignment
Department of Computer Science, University of Virginia, Charlottesville, Virginia, USA（弗吉尼亚大学计算机科学系）；Department of Electrical and Computer Engineering, University of Virginia, Charlottesville, Virginia, USA（弗吉尼亚大学电气与计算机工程系）
ScoreShield: Differentially Private Release of Similarity Scores
School of Engineering and Applied Sciences, Harvard University（哈佛大学工程与应用科学学院）；School of Engineering, École Polytechnique Fédérale de Lausanne (EPFL)（洛桑联邦理工学院工程学院）
An Interactive Framework for Finding the Optimal Trade-off in Differential Privacy
Department of Computer Science, Aalto University, Espoo, Finland（阿莱大学计算机科学系）；Department of Computer Science, University of Helsinki, Helsinki, Finland（赫尔辛基大学计算机科学系）；Department of Computer Science, University of Manchester, Manchester, United Kingdom（曼彻斯特大学计算机科学系）
Improved theoretical guarantee for rank aggregation via spectral method
Shanghai Frontiers Science Center of Artificial Intelligence and Deep Learning（上海人工智能与深度学习前沿科学中心）；New York University Shanghai（上海纽约大学）；Center for Data Science, New York University（纽约大学数据科学中心）；New York University（纽约大学）
