Journal ArticleDOI
Privacy-Preserving Distributed Multi-Task Learning against Inference Attack in Cloud Computing
TLDR
In this paper, a machine learning as a service (MLaaS) has recently been valued by the organizations for machine learning training over SaaS over a period of time.Abstract:
Because of the powerful computing and storage capability in cloud computing, machine learning as a service (MLaaS) has recently been valued by the organizations for machine learning training over s...read more
Citations
More filters
Journal ArticleDOI
Learning in Your “Pocket”: Secure Collaborative Deep Learning With Membership Privacy
TL;DR: Sigma as discussed by the authors is a privacy-preserving collaborative deep learning mechanism, which allows participating organizations to train a collective model without exposing their local training data to the others by using a single-server-aided private collaborative architecture.
Journal ArticleDOI
MP-CLF: An effective Model-Preserving Collaborative deep Learning Framework for mitigating data leakage under the GAN
Journal ArticleDOI
A Review on Security Issues and Solutions for Precision Health in Internet-of-Medical-Things Systems
TL;DR: In this paper , the authors present an IoMT system model consisting of three layers: the sensing layer, the network layer and the cloud infrastructure layer, and discuss the security vulnerabilities and threats, and review the existing security techniques and schemes corresponding to the system components.
Journal ArticleDOI
Multi-Task Model Personalization for Federated Supervised SVM in Heterogeneous Networks
Aleksei Ponomarenko-Timofeev,Olga Galinina,Ravikumar Balakrishnan,Nageen Himayat,V. Andreev,Yevgeni Koucheryavy +5 more
TL;DR: In this paper , an efficient iterative distributed method based on the alternating direction method of multipliers (ADMM) for support vector machines (SVMs), which tackles federated classification and regression, is proposed.
References
More filters
Proceedings ArticleDOI
Membership Inference Attacks Against Machine Learning Models
TL;DR: This work quantitatively investigates how machine learning models leak information about the individual data records on which they were trained and empirically evaluates the inference techniques on classification models trained by commercial "machine learning as a service" providers such as Google and Amazon.
Proceedings ArticleDOI
Privacy-Preserving Deep Learning
Reza Shokri,Vitaly Shmatikov +1 more
TL;DR: This paper presents a practical system that enables multiple parties to jointly learn an accurate neural-network model for a given objective without sharing their input datasets, and exploits the fact that the optimization algorithms used in modern deep learning, namely, those based on stochastic gradient descent, can be parallelized and executed asynchronously.
Proceedings ArticleDOI
Exploiting Unintended Feature Leakage in Collaborative Learning
TL;DR: In this article, passive and active inference attacks are proposed to exploit the leakage of information about participants' training data in federated learning, where each participant can infer the presence of exact data points and properties that hold only for a subset of the training data and are independent of the properties of the joint model.
Journal ArticleDOI
Differentially Private Empirical Risk Minimization
TL;DR: This work proposes a new method, objective perturbation, for privacy-preserving machine learning algorithm design, and shows that both theoretically and empirically, this method is superior to the previous state-of-the-art, output perturbations, in managing the inherent tradeoff between privacy and learning performance.
Journal ArticleDOI
Privacy-Preserving Deep Learning via Additively Homomorphic Encryption
TL;DR: This paper presented a privacy-preserving deep learning system in which many learning participants perform neural network-based deep learning over a combined dataset of all, without revealing the participant's identity.