Privacy-Preserving Collaborative Learning through Feature Extraction

by   Alireza Sarmadi, et al.

We propose a framework in which multiple entities collaborate to build a machine learning model while preserving privacy of their data. The approach utilizes feature embeddings from shared/per-entity feature extractors transforming data into a feature space for cooperation between entities. We propose two specific methods and compare them with a baseline method. In Shared Feature Extractor (SFE) Learning, the entities use a shared feature extractor to compute feature embeddings of samples. In Locally Trained Feature Extractor (LTFE) Learning, each entity uses a separate feature extractor and models are trained using concatenated features from all entities. As a baseline, in Cooperatively Trained Feature Extractor (CTFE) Learning, the entities train models by sharing raw data. Secure multi-party algorithms are utilized to train models without revealing data or features in plain text. We investigate the trade-offs among SFE, LTFE, and CTFE in regard to performance, privacy leakage (using an off-the-shelf membership inference attack), and computational cost. LTFE provides the most privacy, followed by SFE, and then CTFE. Computational cost is lowest for SFE and the relative speed of CTFE and LTFE depends on network architecture. CTFE and LTFE provide the best accuracy. We use MNIST, a synthetic dataset, and a credit card fraud detection dataset for evaluations.


page 3

page 13


Sharing FANCI Features: A Privacy Analysis of Feature Extraction for DGA Detection

The goal of Domain Generation Algorithm (DGA) detection is to recognize ...

Privacy-Preserving Machine Learning for Collaborative Data Sharing via Auto-encoder Latent Space Embeddings

Privacy-preserving machine learning in data-sharing processes is an ever...

Privacy Preserving and Collusion Resistant Energy Sharing

Energy has been increasingly generated or collected by different entitie...

Additively Homomorphical Encryption based Deep Neural Network for Asymmetrically Collaborative Machine Learning

The financial sector presents many opportunities to apply various machin...

Privacy-Preserving Collaborative Prediction using Random Forests

We study the problem of privacy-preserving machine learning (PPML) for e...

AutoSUM: Automating Feature Extraction and Multi-user Preference Simulation for Entity Summarization

Withthegrowthofknowledgegraphs, entity descriptions are becoming extreme...

Multiple Classification with Split Learning

Privacy issues were raised in the process of training deep learning in m...

Please sign up or login with your details

Forgot password? Click here to reset