Improving Adversarial Robustness in Weight-quantized Neural Networks

12/29/2020
by   Chang Song, et al.
0

Neural networks are getting deeper and more computation-intensive nowadays. Quantization is a useful technique in deploying neural networks on hardware platforms and saving computation costs with negligible performance loss. However, recent research reveals that neural network models, no matter full-precision or quantized, are vulnerable to adversarial attacks. In this work, we analyze both adversarial and quantization losses and then introduce criteria to evaluate them. We propose a boundary-based retraining method to mitigate adversarial and quantization losses together and adopt a nonlinear mapping method to defend against white-box gradient-based adversarial attacks. The evaluations demonstrate that our method can better restore accuracy after quantization than other baseline methods on both black-box and white-box adversarial attacks. The results also show that adversarial training suffers quantization loss and does not cooperate well with other training methods.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/23/2021

A Layer-wise Adversarial-aware Quantization Optimization for Improving Robustness

Neural networks are getting better accuracy with higher energy and compu...
research
03/30/2020

Improved Gradient based Adversarial Attacks for Quantized Networks

Neural network quantization has become increasingly popular due to effic...
research
10/17/2022

ODG-Q: Robust Quantization via Online Domain Generalization

Quantizing neural networks to low-bitwidth is important for model deploy...
research
11/01/2017

Attacking Binarized Neural Networks

Neural networks with low-precision weights and activations offer compell...
research
04/17/2019

Defensive Quantization: When Efficiency Meets Robustness

Neural network quantization is becoming an industry standard to efficien...
research
04/08/2023

Benchmarking the Robustness of Quantized Models

Quantization has emerged as an essential technique for deploying deep ne...
research
11/29/2022

Quantization-aware Interval Bound Propagation for Training Certifiably Robust Quantized Neural Networks

We study the problem of training and certifying adversarially robust qua...

Please sign up or login with your details

Forgot password? Click here to reset