کنفرانس مهندسی برق ایران

صفحه اصلی / سی و یکمین کنفرانس بین المللی مهندسی برق

Privacy-Preserving Learning using Autoencoder-based Structure

نویسندگان :

Mohammad Ali Jamshidi¹ Hadi Veisi² Mohammad Mahdi Mojahedian³ Mohammad Reza Aref⁴

1- Sharif university of technology 2- University of Tehran 3- Sharif university of technology 4- Sharif university of technology

کلمات کلیدی :

Privacy،Utility،Deep Neural Networks،Autoencoders

چکیده :

The need for privacy makes data centers not provide their datasets to inference centers. On the other hand, inference centers need more data to train learning algorithms and provide suitable and acceptable services. Therefore, the existence of a structure that can keep the data confidential while maintaining its usefulness for utility providers is of great importance. In this paper, by modifying the structure of the autoencoder, a method is presented that manages the trade-off between utility and privacy. Moreover, the performance of the proposed method has been evaluated by simulation.

لیست مقالات

لیست مقالات بایگانی شده

Anomaly Detection in Urban Water Distribution Grids Using Fog Computing Architecture

Sara Mirzaie - Mohammadreza Avazaghaei - Omid Bushehrian

Transfer learning using deep convolutional neural network for predicting dementia severity

Vahid Asayesh - Mehdi Dehghani - Majid Torabi Nikjeh - Sepideh Akhtari khosrowshahi

Optimization of Fifth Order Band-Pass Ladder Filter and Statistical Analysis of Reverse Problem

Sayyed Ali Alizadeh - Mahmoud Kamarei

Development of a Tilt Bicopter: Experimental Results

Ali Moaveni - Alireza Bahmanyar - Arshia Rezaei - Amin Talaeizadeh - Aria Alasti

A New 10 Watt 1.6 GHz Linear Power Amplifier with More than 11 dB Gain

Marzieh Chegini - HojjatAllah Nemati - Mahmoud Kamarei

Accurate Methods for Automatic Detection of Characteristic Points in Electrocardiograms

Seyedeh Mersedeh Bagheri - Mohammad Pooyan

Iranian stock market fluctuations: from social news to forecasting models

Maryam Sharifinia - Farzaneh Ghayour Baghbani

True Class-E Design For Inductive Coupling Wireless Power Transfer Applications

Ali Asghar Razavi Haeri - Aminghasem Safarian - Ali Fotowat-Ahmady

A Highly-Linear Wideband Differential Low-Noise Amplifier Using Derivative Superposition Technique

Abolfazl Rajaiyan - Mehdi Saberi

Stochastic model predictive control based on online learning for a class of nonlinear constrained systems

Mahdi Mansoury - Mohammad Ali Badamchizadeh - Hamed Kharrati

بیشتر

ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 42.5.3