Related papers: Exploring Machine Learning Privacy/Utility trade-o…

Federated learning has emerged as an attractive approach to protect data privacy by eliminating the need for sharing clients' data while reducing communication costs compared with centralized machine learning algorithms. However, recent…

Ensuring the privacy of sensitive training data is crucial in privacy-preserving machine learning. However, in practical scenarios, privacy protection may be required for only a subset of features. For instance, in ICU data, demographic…

This paper focuses on the problem of Differentially Private Stochastic Optimization for (multi-layer) fully connected neural networks with a single output node. In the first part, we examine cases with no hidden nodes, specifically focusing…

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…

Current practices for reporting the level of differential privacy (DP) protection for machine learning (ML) algorithms such as DP-SGD provide an incomplete and potentially misleading picture of the privacy guarantees. For instance, if only…

Deep learning models have been extensively adopted in various regions due to their ability to represent hierarchical features, which highly rely on the training set and procedures. Thus, protecting the training process and deep learning…

With increasing usage of deep learning algorithms in many application, new research questions related to privacy and adversarial attacks are emerging. However, the deep learning algorithm improvement needs more and more data to be shared…

Machine Learning (ML) models integrated with in-situ sensing offer transformative solutions for defect detection in Additive Manufacturing (AM), but this integration brings critical challenges in safeguarding sensitive data, such as part…

Deep learning holds immense promise for aiding radiologists in breast cancer detection. However, achieving optimal model performance is hampered by limitations in availability and sharing of data commonly associated to patient privacy…

With rise of machine learning (ML) and the proliferation of smart mobile devices, recent years have witnessed a surge of interest in performing ML in wireless edge networks. In this paper, we consider the problem of jointly improving data…

We investigate practical and scalable algorithms for training large language models (LLMs) with user-level differential privacy (DP) in order to provably safeguard all the examples contributed by each user. We study two variants of DP-SGD…

Significant success has been realized recently on applying machine learning to real-world applications. There have also been corresponding concerns on the privacy of training data, which relates to data security and confidentiality issues.…

Differential privacy (DP) is a compelling privacy definition that explains the privacy-utility tradeoff via formal, provable guarantees. Inspired by recent progress toward general-purpose data release algorithms, we propose a private…

Protecting data privacy in deep learning (DL) is of crucial importance. Several celebrated privacy notions have been established and used for privacy-preserving DL. However, many existing mechanisms achieve privacy at the cost of…

Collaborative machine learning techniques such as federated learning (FL) enable the training of models on effectively larger datasets without data transfer. Recent initiatives have demonstrated that segmentation models trained with FL can…

Differential privacy (DP) has become the de facto standard of privacy preservation due to its strong protection and sound mathematical foundation, which is widely adopted in different applications such as big data analysis, graph data…

Balancing differential privacy (DP) with recommendation accuracy is a key challenge in privacy-preserving recommender systems, since DP-noise degrades accuracy. We address this trade-off at both the data and model levels. At the data level,…

Differentially private stochastic gradient descent (DP-SGD) is broadly considered to be the gold standard for training and fine-tuning neural networks under differential privacy (DP). With the increasing availability of high-quality…

Data engineering often requires accuracy (utility) constraints on results, posing significant challenges in designing differentially private (DP) mechanisms, particularly under stringent privacy parameter $\epsilon$. In this paper, we…

Parameter-transfer is a well-known and versatile approach for meta-learning, with applications including few-shot learning, federated learning, and reinforcement learning. However, parameter-transfer algorithms often require sharing models…