Related papers: Power Mechanism: Private Tabular Representation Re…

Recommendation models can effectively estimate underlying user interests and predict one's future behaviors by factorizing an observed user-item rating matrix into products of two sets of latent factors. However, the user-specific embedding…

Pretrained encoders for mathematical texts have achieved significant improvements on various tasks such as formula classification and information retrieval. Yet they remain limited in representing and capturing student strategies for entire…

While many deep learning models trained on private datasets have been deployed in various practical tasks, they may pose a privacy leakage risk as attackers could recover informative data or label knowledge from models. In this work, we…

We introduce a deep learning framework able to deal with strong privacy constraints. Based on collaborative learning, differential privacy and homomorphic encryption, the proposed approach advances state-of-the-art of private deep learning…

We study private synthetic data generation for query release, where the goal is to construct a sanitized version of a sensitive dataset, subject to differential privacy, that approximately preserves the answers to a large collection of…

The use of mutual information as a tool in private data sharing has remained an open challenge due to the difficulty of its estimation in practice. In this paper, we propose InfoShape, a task-based encoder that aims to remove unnecessary…

Deep neural networks are increasingly being used in a variety of machine learning applications applied to rich user data on the cloud. However, this approach introduces a number of privacy and efficiency challenges, as the cloud operator…

Model personalization allows a set of individuals, each facing a different learning task, to train models that are more accurate for each person than those they could develop individually. The goals of personalization are captured in a…

In this paper, we propose a novel method for enhancing security in privacy-preserving federated learning using the Vision Transformer. In federated learning, learning is performed by collecting updated information without collecting raw…

There has been a recent wave of interest in intermediate trust models for differential privacy that eliminate the need for a fully trusted central data collector, but overcome the limitations of local differential privacy. This interest has…

Speaker embeddings are ubiquitous, with applications ranging from speaker recognition and diarization to speech synthesis and voice anonymisation. The amount of information held by these embeddings lends them versatility, but also raises…

One of the big challenges in machine learning applications is that training data can be different from the real-world data faced by the algorithm. In language modeling, users' language (e.g. in private messaging) could change in a year and…

Edge-cloud collaborative inference empowers resource-limited IoT devices to support deep learning applications without disclosing their raw data to the cloud server, thus preserving privacy. Nevertheless, prior research has shown that…

The availability of rich and vast data sources has greatly advanced machine learning applications in various domains. However, data with privacy concerns comes with stringent regulations that frequently prohibited data access and data…

Public pretraining is a promising approach to improve differentially private model training. However, recent work has noted that many positive research results studying this paradigm only consider in-distribution tasks, and may not apply to…

Learning from data owned by several parties, as in federated learning, raises challenges regarding the privacy guarantees provided to participants and the correctness of the computation in the presence of malicious parties. We tackle these…

Privacy-preserving distributed machine learning becomes increasingly important due to the recent rapid growth of data. This paper focuses on a class of regularized empirical risk minimization (ERM) machine learning problems, and develops…

The success of large neural networks is crucially determined by the availability of data. It has been observed that training only on a small amount of public data, or privately on the abundant private data can lead to undesirable…

In the classical multi-party computation setting, multiple parties jointly compute a function without revealing their own input data. We consider a variant of this problem, where the input data can be shared for machine learning training…

Federated Learning enables diverse devices to collaboratively train a shared model while keeping training data locally stored, avoiding the need for centralized cloud storage. Despite existing privacy measures, concerns arise from potential…