说服性隐私

Efficient Privacy-Preserved Processing of Multimodal Data for Vehicular Traffic Analysis

We estimate vehicular traffic states from multimodal data collected by single-loop detectors while preserving the privacy of the individual vehicles contributing to the data. To this end, we propose a novel hybrid differential privacy (DP) approach that utilizes minimal randomization to preserve privacy by taking advantage of the relevant traffic state dynamics and the concept of DP sensitivity. Through theoretical analysis and experiments with real-world data, we show that the proposed approach significantly outperforms the related baseline non-private and private approaches in terms of accur…

具有差分隐私的序列变化检测

Sequential Change Detection with Differential Privacy

本文提出DP-CUSUM方法，在保证差分隐私的前提下，实现序列变化检测的最优性能。

基于差分隐私的大间隔多类高斯分类

Large Margin Multiclass Gaussian Classification with Differential Privacy

随着越来越多的敏感个人信息被聚集到数据存储库中，开发用于处理数据而不泄露关于个体数据实例的信息的机制变得重要。差分隐私模型为这种机制的发展和理论分析提供了一个框架。在本文中，我们提出了一种算法，用于学习一个判别式训练的多类高斯分类器，满足差分隐私使用一个大的利润损失函数与扰动正则化项。我们提出了一个理论上的上限的扰动引入的分类器的超额风险。

Provable Membership Inference Privacy

In applications involving sensitive data, such as finance and healthcare, the necessity for preserving data privacy can be a significant barrier to machine learning model development. Differential privacy (DP) has emerged as one canonical standard for provable privacy. However, DP's strong theoretical guarantees often come at the cost of a large drop in its utility for machine learning, and DP guarantees themselves can be difficult to interpret. In this work, we propose a novel privacy notion, membership inference privacy (MIP), to address these challenges. We give a precise characterization o…

Generalization in Generative Adversarial Networks: A Novel Perspective from Privacy Protection

In this paper, we aim to understand the generalization properties of generative adversarial networks (GANs) from a new perspective of privacy protection. Theoretically, we prove that a differentially private learning algorithm used for training the GAN does not overfit to a certain degree, i.e., the generalization gap can be bounded. Moreover, some recent works, such as the Bayesian GAN, can be re-interpreted based on our theoretical insight from privacy protection. Quantitatively, to evaluate the information leakage of well-trained GAN models, we perform various membership attacks on these mo…

你的注意力有多私密？弥合隐私与上下文学习之间的鸿沟

How Private is Your Attention? Bridging Privacy with In-Context Learning

本文提出线性注意力头的差分隐私预训练算法，首次理论分析线性回归中上下文学习的隐私-准确性权衡，并证明其对对抗性扰动的鲁棒性。

pMSE Mechanism: Differentially Private Synthetic Data with Maximal Distributional Similarity

We propose a method for the release of differentially private synthetic datasets. In many contexts, data contain sensitive values which cannot be released in their original form in order to protect individuals' privacy. Synthetic data is a protection method that releases alternative values in place of the original ones, and differential privacy (DP) is a formal guarantee for quantifying the privacy loss. We propose a method that maximizes the distributional similarity of the synthetic data relative to the original data using a measure known as the pMSE, while guaranteeing epsilon-differential …

Channel Leakage, Information-Theoretic Limitations of Obfuscation, and Optimal Privacy Mask Design for Streaming Data

In this paper, we first introduce the notion of channel leakage as the minimum mutual information between the channel input and channel output. As its name indicates, channel leakage quantifies the minimum information leakage to the malicious receiver. In a broad sense, it can be viewed as a dual concept of channel capacity, which characterizes the maximum information transmission to the targeted receiver. We obtain explicit formulas of channel leakage for the white Gaussian case, the colored Gaussian case, and the fading case. We then utilize this notion to investigate the fundamental limitat…