DeepAI AI Chat
Log In Sign Up

Reconstruction of Privacy-Sensitive Data from Protected Templates

by   Shideh Rezaeifar, et al.

In this paper, we address the problem of data reconstruction from privacy-protected templates, based on recent concept of sparse ternary coding with ambiguization (STCA). The STCA is a generalization of randomization techniques which includes random projections, lossy quantization, and addition of ambiguization noise to satisfy the privacy-utility trade-off requirements. The theoretical privacy-preserving properties of STCA have been validated on synthetic data. However, the applicability of STCA to real data and potential threats linked to reconstruction based on recent deep reconstruction algorithms are still open problems. Our results demonstrate that STCA still achieves the claimed theoretical performance when facing deep reconstruction attacks for the synthetic i.i.d. data, while for real images special measures are required to guarantee proper protection of the templates.


page 1

page 2

page 3

page 4


A Linear Reconstruction Approach for Attribute Inference Attacks against Synthetic Data

Personal data collected at scale from surveys or digital devices offers ...

Rethinking Privacy Preserving Deep Learning: How to Evaluate and Thwart Privacy Attacks

This paper investigates capabilities of Privacy-Preserving Deep Learning...

Privacy-Preserving SVM Computing by Using Random Unitary Transformation

A privacy-preserving Support Vector Machine (SVM) computing scheme is pr...

TAPAS: a Toolbox for Adversarial Privacy Auditing of Synthetic Data

Personal data collected at scale promises to improve decision-making and...

Privacy-Preserving Synthetic Educational Data Generation

Institutions collect massive learning traces but they may not disclose i...

Privacy-Preserving Near Neighbor Search via Sparse Coding with Ambiguation

In this paper, we propose a framework for privacy-preserving approximate...

A Common Semantic Model of the GDPR Register of Processing Activities

The creation and maintenance of a Register of Processing Activities (ROP...