Related papers: DPMLBench: Holistic Evaluation of Differentially P…

Differential privacy (DP) is the de facto standard for training machine learning (ML) models, including neural networks, while ensuring the privacy of individual examples in the training set. Despite a rich literature on how to train ML…

Differential privacy (DP) is widely employed to provide privacy protection for individuals by limiting information leakage from the aggregated data. Two well-known models of DP are the central model and the local model. The former requires…

Data-driven advancements significantly contribute to societal progress, yet they also pose substantial risks to privacy. In this landscape, differential privacy (DP) has become a cornerstone in privacy preservation efforts. However, the…

Differential Privacy (DP) is a well-established framework to quantify privacy loss incurred by any algorithm. Traditional DP formulations impose a uniform privacy requirement for all users, which is often inconsistent with real-world…

As Edge Intelligence (EI) becomes increasingly prevalent in domains such as smart healthcare, manufacturing, and critical infrastructure, ensuring data privacy while maintaining system efficiency is a growing challenge. This paper presents…

We present a novel method for accurately auditing the differential privacy (DP) guarantees of DP mechanisms. In particular, our solution is applicable to auditing DP guarantees of machine learning (ML) models. Previous auditing methods…

The shuffle model of differential privacy (DP) offers compelling privacy-utility trade-offs in decentralized settings (e.g., internet of things, mobile edge networks). Particularly, the multi-message shuffle model, where each user may…

Split learning is a distributed training framework that allows multiple parties to jointly train a machine learning model over vertically partitioned data (partitioned by attributes). The idea is that only intermediate computation results,…

With the increasing emphasis on privacy regulations, such as GDPR, protecting individual privacy and ensuring compliance have become critical concerns for both individuals and organizations. Privacy-preserving machine learning (PPML) is an…

Label differential privacy (DP) is designed for learning problems involving private labels and public features. While various methods have been proposed for learning under label DP, the theoretical limits remain largely unexplored. In this…

Collecting and analyzing massive data generated from smart devices have become increasingly pervasive in crowdsensing, which are the building blocks for data-driven decision-making. However, extensive statistics and analysis of such data…

In this paper, we show that the process of continually learning new tasks and memorizing previous tasks introduces unknown privacy risks and challenges to bound the privacy loss. Based upon this, we introduce a formal definition of Lifelong…

We study the task of training regression models with the guarantee of label differential privacy (DP). Based on a global prior distribution on label values, which could be obtained privately, we derive a label DP randomization mechanism…

Large language models (LLMs) are commonly adapted to downstream tasks through fine-tuning, but fine-tuning data often contains sensitive information that may be leaked by the resulting model. Differential privacy (DP) offers formal…

Differential Privacy (DP) has emerged as a robust framework for privacy-preserving data releases and has been successfully applied in high-profile cases, such as the 2020 US Census. However, in organizational settings, the use of DP remains…

Differential Privacy (DP) is a mathematical framework that is increasingly deployed to mitigate privacy risks associated with machine learning and statistical analyses. Despite the growing adoption of DP, its technical privacy parameters do…

While Federated Learning (FL) mitigates direct data exposure, the resulting trained models remain susceptible to membership inference attacks (MIAs). This paper presents an empirical evaluation of Differential Privacy (DP) as a defense…

Metric Differential Privacy (mDP) builds upon the core principles of Differential Privacy (DP) by incorporating various distance metrics, which offer adaptable and context-sensitive privacy guarantees for a wide range of applications, such…

The tension between data privacy and model utility has become the defining bottleneck for the practical deployment of large language models (LLMs) trained on sensitive corpora including healthcare. Differentially private stochastic gradient…

Traditional differential privacy is independent of the data distribution. However, this is not well-matched with the modern machine learning context, where models are trained on specific data. As a result, achieving meaningful privacy…