AutoGAN-based Dimension Reduction for Privacy Preservation

by   Hung Nguyen, et al.

Exploiting data and concurrently protecting sensitive information to whom data belongs is an emerging research area in data mining. Several methods have been introduced to protect individual privacy and at the same time maximize data utility. Unfortunately, existing techniques such as differential privacy are not effectively protecting data owner privacy in the scenarios using visualizable data (e.g., images, videos). Furthermore, such techniques usually result in low performance with a high number of queries. To address these problems, we propose a dimension reduction-based method for privacy preservation. This method generates dimensionally-reduced data for performing machine learning tasks and prevents a strong adversary from reconstructing the original data. In this paper, we first introduce a theoretical tool to evaluate dimension reduction-based privacy preserving mechanisms, then propose a non-linear dimension reduction framework using state-of-the-art neural network structures for privacy preservation. In the experiments, we test our method on popular face image datasets and show that our method can retain data utility and resist data reconstruction, thus protecting privacy.


page 7

page 10


Differential Privacy in Privacy-Preserving Big Data and Learning: Challenge and Opportunity

Differential privacy (DP) has become the de facto standard of privacy pr...

DataLens: Scalable Privacy Preserving Training via Gradient Compression and Aggregation

Recent success of deep neural networks (DNNs) hinges on the availability...

Model Order Reduction based on Runge-Kutta Neural Network

Model Order Reduction (MOR) methods enable the generation of real-time-c...

Parameter-free Network Sparsification and Data Reduction by Minimal Algorithmic Information Loss

The study of large and complex datasets, or big data, organized as netwo...

Dimension reduction, exact recovery, and error estimates for sparse reconstruction in phase space

An important theme in modern inverse problems is the reconstruction of t...

Non-linear dimension reduction in factor-augmented vector autoregressions

This paper introduces non-linear dimension reduction in factor-augmented...

Distribution-Preserving k-Anonymity

Preserving the privacy of individuals by protecting their sensitive attr...

Please sign up or login with your details

Forgot password? Click here to reset