A Privacy-Preserving DNN Pruning and Mobile Acceleration Framework

03/13/2020
by   Zheng Zhan, et al.
0

To facilitate the deployment of deep neural networks (DNNs) on resource-constrained computing systems, DNN model compression methods have been proposed. However, previous methods mainly focus on reducing the model size and/or improving hardware performance, without considering the data privacy requirement. This paper proposes a privacy-preserving model compression framework that formulates a privacy-preserving DNN weight pruning problem and develops an ADMM based solution to support different weight pruning schemes. We consider the case that the system designer will perform weight pruning on a pre-trained model provided by the client, whereas the client cannot share her confidential training dataset. To mitigate the non-availability of the training dataset, the system designer distills the knowledge of a pre-trained model into a pruned model using only randomly generated synthetic data. Then the client's effort is simply reduced to performing the retraining process using her confidential training dataset, which is similar as the DNN training process with the help of the mask function from the system designer. Both algorithmic and hardware experiments validate the effectiveness of the proposed framework.

READ FULL TEXT

page 1

page 2

page 3

page 4

page 5

page 6

page 7

page 8

research
08/29/2019

An Ultra-Efficient Memristor-Based DNN Framework with Structured Weight Pruning and Quantization Using ADMM

The high computation and memory storage of large deep neural networks (D...
research
05/25/2021

AutoReCon: Neural Architecture Search-based Reconstruction for Data-free Compression

Data-free compression raises a new challenge because the original traini...
research
08/28/2020

MCMIA: Model Compression Against Membership Inference Attack in Deep Neural Networks

Deep learning or deep neural networks (DNNs) have nowadays enabled high ...
research
07/10/2022

One-shot Neural Backdoor Erasing via Adversarial Weight Masking

Recent studies show that despite achieving high accuracy on a number of ...
research
08/24/2022

Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning

We consider the problem of model compression for deep neural networks (D...
research
12/03/2019

The Knowledge Within: Methods for Data-Free Model Compression

Background: Recently, an extensive amount of research has been focused o...
research
10/15/2020

An Algorithm for Learning Smaller Representations of Models With Scarce Data

We present a greedy algorithm for solving binary classification problems...

Please sign up or login with your details

Forgot password? Click here to reset