Related papers: Efficient Private Machine Learning by Differentiab…

In this work, we propose a novel framework for privacy-preserving client-distributed machine learning. It is motivated by the desire to achieve differential privacy guarantees in the local model of privacy in a way that satisfies all…

We study the privatization of distributed learning and optimization strategies. We focus on differential privacy schemes and study their effect on performance. We show that the popular additive random perturbation scheme degrades…

Differential privacy (DP) has become the standard for private data analysis. Certain machine learning applications only require privacy protection for specific protected attributes. Using naive variants of differential privacy in such use…

Privacy-preserving technologies have introduced a paradigm shift that allows for realizable secure computing in real-world systems. The significant barrier to the practical adoption of these primitives is the computational and communication…

Differential Privacy has become a widely popular method for data protection in machine learning, especially since it allows formulating strict mathematical privacy guarantees. This survey provides an overview of the state-of-the-art of…

Machine learning models benefit from large and diverse datasets. Using such datasets, however, often requires trusting a centralized data aggregator. For sensitive applications like healthcare and finance this is undesirable as it could…

Over the past few years, a tremendous growth of machine learning was brought about by a significant increase in adoption and implementation of cloud-based services. As a result, various solutions have been proposed in which the machine…

The financial sector presents many opportunities to apply various machine learning techniques. Centralized machine learning creates a constraint which limits further applications in finance sectors. Data privacy is a fundamental challenge…

With the extensive applications of machine learning, the issue of private or sensitive data in the training examples becomes more and more serious: during the training process, personal information or habits may be disclosed to unexpected…

Machine learning (ML) classifiers are invaluable building blocks that have been used in many fields. High quality training dataset collected from multiple data providers is essential to train accurate classifiers. However, it raises concern…

Precision medicine is an emerging approach for disease treatment and prevention that delivers personalized care to individual patients by considering their genetic makeups, medical histories, environments, and lifestyles. Despite the rapid…

Homomorphic encryption enables arbitrary computation over data while it remains encrypted. This privacy-preserving feature is attractive for machine learning, but requires significant computational time due to the large overhead of the…

A typical setup in many machine learning scenarios involves a server that holds a model and a user that possesses data, and the challenge is to perform inference while safeguarding the privacy of both parties. Private Inference has been…

Medical data is often highly sensitive in terms of data privacy and security concerns. Federated learning, one type of machine learning techniques, has been started to use for the improvement of the privacy and security of medical data. In…

Outsourced computation for neural networks allows users access to state of the art models without needing to invest in specialized hardware and know-how. The problem is that the users lose control over potentially privacy sensitive data.…

Deep learning models are often trained on datasets that contain sensitive information such as individuals' shopping transactions, personal contacts, and medical records. An increasingly important line of work therefore has sought to train…

Privacy preserving in machine learning is a crucial issue in industry informatics since data used for training in industries usually contain sensitive information. Existing differentially private machine learning algorithms have not…

In many real-world applications of machine learning, data are distributed across many clients and cannot leave the devices they are stored on. Furthermore, each client's data, computational resources and communication constraints may be…

We introduce an end-to-end private deep learning framework, applied to the task of predicting 30-day readmission from electronic health records. By using differential privacy during training and homomorphic encryption during inference, we…

When applying differential privacy to sensitive data, we can often improve performance using external information such as other sensitive data, public data, or human priors. We propose to use the learning-augmented algorithms (or algorithms…