Related papers: Fine-Tuning Language Models with Differential Priv…
This paper introduces FairDP, a novel training mechanism designed to provide group fairness certification for the trained model's decisions, along with a differential privacy (DP) guarantee to protect training data. The key idea of FairDP…
Split learning (SL) aims to protect user data privacy by distributing deep models between client-server and keeping private data locally. Only processed or `smashed' data can be transmitted from the clients to the server during the SL…
The rapid advancement of large language models (LLMs) has revolutionized natural language processing, enabling applications in diverse domains such as healthcare, finance and education. However, the growing reliance on extensive data for…
Anonymizing textual documents is a highly context-sensitive problem: the appropriate balance between privacy protection and utility preservation varies with the data domain, privacy objectives, and downstream application. However, existing…
The nonparametric variational information bottleneck (NVIB) provides the foundation for nonparametric variational differential privacy (NVDP), a framework for building privacy-preserving language models. However, the learned latent…
Federated learning (FL) enables collaborative model training across distributed clients without sharing raw data, making it a promising approach for privacy-preserving machine learning. However, ensuring differential privacy (DP) in FL…
Applications of Differential Privacy (DP) in NLP must distinguish between the syntactic level on which a proposed mechanism operates, often taking the form of $\textit{word-level}$ or $\textit{document-level}$ privatization. Recently,…
While Local Differential Privacy (LDP) serves as a foundational primitive for distributed data collection, its stringent noise injection requirement often leads to severe degradation in data utility. This degradation stems from the…
We propose a novel mechanism for answering sets of count- ing queries under differential privacy. Given a workload of counting queries, the mechanism automatically selects a different set of "strategy" queries to answer privately, using…
Differential privacy (DP) has arisen as the gold standard in protecting an individual's privacy in datasets by adding calibrated noise to each data sample. While the application to categorical data is straightforward, its usability in the…
We describe a new algorithm for answering a given set of range queries under $\epsilon$-differential privacy which often achieves substantially lower error than competing methods. Our algorithm satisfies differential privacy by adding noise…
We design a class of additive noise mechanisms that satisfy \((\varepsilon, \delta)\)-differential privacy (DP) for scalar, real-valued query functions with known sensitivities, with a particular focus on moderate and low-privacy regimes.…
Federated learning (FL), as a type of collaborative machine learning framework, is capable of preserving private data from mobile terminals (MTs) while training the data into useful models. Nevertheless, from a viewpoint of information…
Differential privacy is often applied with a privacy parameter that is larger than the theory suggests is ideal; various informal justifications for tolerating large privacy parameters have been proposed. In this work, we consider partial…
In this paper, we present a notion of differential privacy (DP) for data that comes from different classes. Here, the class-membership is private information that needs to be protected. The proposed method is an output perturbation…
Speech pathology has impacts on communication abilities and quality of life. While deep learning-based models have shown potential in diagnosing these disorders, the use of sensitive data raises critical privacy concerns. Although…
With the increasing use of cloud-based services for training and deploying machine learning models, data privacy has become a major concern. This is particularly important for natural language processing (NLP) models, which often process…
Many applications of machine learning, such as human health research, involve processing private or sensitive information. Privacy concerns may impose significant hurdles to collaboration in scenarios where there are multiple sites holding…
An important problem in deep learning is the privacy and security of neural networks (NNs). Both aspects have long been considered separately. To date, it is still poorly understood how privacy enhancing training affects the robustness of…
We study distributed estimation and learning problems in a networked environment where agents exchange information to estimate unknown statistical properties of random variables from their privately observed samples. The agents can…