Search for: All records

Data synthesis has been advocated as an important approach for utilizing data while protecting data privacy. In recent years, a plethoraof tabular data synthesis algorithms (i.e., synthesizers) have beenproposed. Some synthesizers satisfy Differential Privacy, while oth-ers aim to provide privacy in a heuristic fashion. A comprehensiveunderstanding of the strengths and weaknesses of these synthe-sizers remains elusive due to drawbacks in evaluation metrics andmissing head-to-head comparisons of newly developed synthesizersthat take advantage of diffusion models and large language modelswith state-of-the-art statistical synthesizers.In this paper, we present a systematic evaluation frameworkfor assessing tabular data synthesis algorithms. Specifically, weexamine and critique existing evaluation metrics, and introducea set of new metrics in terms of fidelity, privacy, and utility toaddress their limitations. We conducted extensive evaluations of8 different types of synthesizers on 12 real-world datasets andidentified some interesting findings, which offer new directions forprivacy-preserving data synthesis. 

Deep learning has shown incredible potential across a wide array of tasks, and accompanied by this growth has been an insatiable appetite for data. However, a large amount of data needed for enabling deep learning is stored on personal devices, and recent concerns on privacy have further highlighted challenges for accessing such data. As a result, federated learning (FL) has emerged as an important privacy-preserving technology that enables collaborative training of machine learning models without the need to send the raw, potentially sensitive, data to a central server. However, the fundamental premise that sending model updates to a server is privacy-preserving only holds if the updates cannot be “reverse engineered” to infer information about the private training data. It has been shown under a wide variety of settings that this privacy premise doesnothold. In this article we provide a comprehensive literature review of the different privacy attacks and defense methods in FL. We identify the current limitations of these attacks and highlight the settings in which the privacy of an FL client can be broken. We further dissect some of the successful industry applications of FL and draw lessons for future successful adoption. We survey the emerging landscape of privacy regulation for FL and conclude with future directions for taking FL toward the cherished goal of generating accurate models while preserving the privacy of the data from its participants. 

Federated learning collaboratively trains a neural network on a global server, where each local client receives the current global model weights and sends back parameter updates (gradients) based on its local private data. The process of sending these model updates may leak client’s private data information. Existing gradient inversion attacks can exploit this vulnerability to recover private training instances from a client’s gradient vectors. Recently, researchers have proposed advanced gradient inversion techniques that existing defenses struggle to handle effectively. In this work, we present a novel defense tailored for large neural network models. Our defense capitalizes on the high dimensionality of the model parameters to perturb gradients within a subspace orthogonal to the original gradient. By leveraging cold posteriors over orthogonal subspaces, our defense implements a refined gradient update mechanism. This enables the selection of an optimal gradient that not only safeguards against gradient inversion attacks but also maintains model utility. We conduct comprehensive experiments across three different datasets and evaluate our defense against various state-of-the-art attacks and defenses. Code is available at https://censor-gradient.github.io.