Related papers: Publishing Neural Networks in Drug Discovery Might…
Privacy-preserving deep learning is crucial for deploying deep neural network based solutions, especially when the model works on data that contains sensitive information. Most privacy-preserving methods lead to undesirable performance…
Prior approaches for membership privacy preservation usually update or retrain all weights in neural networks, which is costly and can lead to unnecessary utility loss or even more serious misalignment in predictions between training data…
In order to both learn and protect sensitive training data, there has been a growing interest in privacy preserving machine learning methods. Differential privacy has emerged as an important measure of privacy. We are interested in the…
We present a framework to statistically audit the privacy guarantee conferred by a differentially private machine learner in practice. While previous works have taken steps toward evaluating privacy loss through poisoning attacks or…
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…
The field of artificial intelligence (AI) has experienced remarkable progress in recent years, driven by the widespread adoption of open-source machine learning models in both research and industry. Considering the resource-intensive nature…
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…
Despite being prevalent in the general field of Natural Language Processing (NLP), pre-trained language models inherently carry privacy and copyright concerns due to their nature of training on large-scale web-scraped data. In this paper,…
In this manuscript, we consider the problem of privacy-preserving training of neural networks in the mere homomorphic encryption setting. We combine several exsiting techniques available, extend some of them, and finally enable the training…
Privacy data protection in the medical field poses challenges to data sharing, limiting the ability to integrate data across hospitals for training high-precision auxiliary diagnostic models. Traditional centralized training methods are…
The combination of deep neural networks and Differential Privacy has been of increasing interest in recent years, as it offers important data protection guarantees to the individuals of the training datasets used. However, using…
Recently, researchers have successfully employed Graph Neural Networks (GNNs) to build enhanced recommender systems due to their capability to learn patterns from the interaction between involved entities. In addition, previous studies have…
Is overparameterization a privacy liability? In this work, we study the effect that the number of parameters has on a classifier's vulnerability to membership inference attacks. We first demonstrate how the number of parameters of a model…
Machine learning can have major societal impact in computational biology applications. In particular, it plays a central role in the development of precision medicine, whereby treatment is tailored to the clinical or genetic features of the…
Deep neural networks are vulnerable to adversarial attacks, such as backdoor attacks in which a malicious adversary compromises a model during training such that specific behaviour can be triggered at test time by attaching a specific word…
We survey distributed deep learning models for training or inference without accessing raw data from clients. These methods aim to protect confidential patterns in data while still allowing servers to train models. The distributed deep…
Federated learning has been proposed as a privacy-preserving machine learning framework that enables multiple clients to collaborate without sharing raw data. However, client privacy protection is not guaranteed by design in this framework.…
Secure multiparty computation (MPC) has been proposed to allow multiple mutually distrustful data owners to jointly train machine learning (ML) models on their combined data. However, by design, MPC protocols faithfully compute the training…
Transfer learning through the use of pre-trained models has become a growing trend for the machine learning community. Consequently, numerous pre-trained models are released online to facilitate further research. However, it raises…
This paper investigates the potential privacy risks associated with forecasting models, with specific emphasis on their application in the context of smart grids. While machine learning and deep learning algorithms offer valuable utility,…