Code-Bridged Classifier (CBC): A Low or Negative Overhead Defense for Making a CNN Classifier Robust Against Adversarial Attacks

TOP Literature Database Code-Bridged Classifier (CBC): A Low or Negative Overhead Defense for Making a CNN Classifier Robust Against Adversarial Attacks

arxiv

AI Security Portal bot

Information in the literature database is collected automatically.

Source

https://arxiv.org/abs/2001.06099

PDF

https://arxiv.org/pdf/2001.06099

Paper Information

Author: Farnaz Behnia,Ali Mirzaeian,Mohammad Sabokrou,Sai Manoj,Tinoosh Mohsenin,Khaled N. Khasawneh,Liang Zhao,Houman Homayoun,Avesta Sasan
Published: 1-17-2020
Affiliation: George Mason University
Country: United States of America
Conference: IEEE International Symposium on Quality Electronic Design (ISQED)

Labels Estimated by AI

Adversarial Example Adversarial Learning Computational Complexity

These labels were automatically added by AI and may be inaccurate.
For details, see About Literature Database.

Abstract

In this paper, we propose Code-Bridged Classifier (CBC), a framework for making a Convolutional Neural Network (CNNs) robust against adversarial attacks without increasing or even by decreasing the overall models' computational complexity. More specifically, we propose a stacked encoder-convolutional model, in which the input image is first encoded by the encoder module of a denoising auto-encoder, and then the resulting latent representation (without being decoded) is fed to a reduced complexity CNN for image classification. We illustrate that this network not only is more robust to adversarial examples but also has a significantly lower computational complexity when compared to the prior art defenses.