AutoGAN-based Dimension Reduction for Privacy Preservation

Abstract

Protecting sensitive information against data exploiting attacks is an emerging research area in data mining. Over the past, several different methods have been introduced to protect individual privacy from such attacks while maximizing data-utility of the application. However, these existing techniques are not sufficient to effectively protect data owner privacy, especially in the scenarios that utilize visualizable data (e.g. images, videos) or the applications that require heavy computations for implementation. To address these problems, we propose a new dimension reduction-based method for privacy preservation. Our method generates dimension-reduced data for performing machine learning tasks and prevents a strong adversary from reconstructing the original data. We first introduce a theoretical approach to evaluate dimension reduction-based privacy preserving mechanisms, then propose a non-linear dimension reduction framework motivated by state-of-the-art neural network structures for privacy preservation. We conducted experiments over three different face image datasets (AT&T, YaleB, and CelebA), and the results show that when the number of dimensions is reduced to seven, we can achieve the accuracies of 79%, 80%, and 73% respectively and the reconstructed images are not recognizable to naked human eyes.

References in corpus (8)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• CryptoDL: Deep Neural Networks over Encrypted Data
• Deep Models Under the GAN: Information Leakage from Collaborative Deep Learning
• Functional Mechanism: Regression Analysis under Differential Privacy
• Generative Adversarial Privacy
• Towards Privacy-Preserving Visual Recognition via Adversarial Training: A Pilot Study
• Understanding Compressive Adversarial Privacy
• Differential Privacy with Compression

Cited by in corpus (10)

• Discriminative Adversarial Domain Generalization with Meta-learning based Cross-domain Validation
• Differentially Private Synthetic Data: Applied Evaluations and Enhancements
• Generative Adversarial Networks: A Survey Towards Private and Secure Applications
• Federated Learning System without Model Sharing through Integration of Dimensional Reduced Data Representations
• ESAI: Efficient Split Artificial Intelligence via Early Exiting Using Neural Architecture Search
• Accuracy and Privacy Evaluations of Collaborative Data Analysis
• SAIA: Split Artificial Intelligence Architecture for Mobile Healthcare System
• SMAP: A Joint Dimensionality Reduction Scheme for Secure Multi-Party Visualization
• Data Collaboration Analysis with Orthonormal Basis Selection and Alignment
• Complementary Ensemble Learning