Ensemble MagNet:A fast training network against adversarial examples

Zebin Zhuang

doi:10.1117/12.2679119

8 May 2023 Ensemble MagNet:A fast training network against adversarial examples

Zebin Zhuang

Proceedings Volume 12635, Second International Conference on Algorithms, Microchips, and Network Applications (AMNA 2023); 126351L (2023) https://doi.org/10.1117/12.2679119
Event: International Conference on Algorithms, Microchips, and Network Applications 2023, 2023, Zhengzhou, China

Abstract

In recent years, deep learning has excellent applications in many fields, especially in computer vision. However, it has been found that deep learning systems are vulnerable to subtle interference, which is almost imperceptible to humans. This leads to model decision errors and potentially disastrous consequences. Therefore, AI scientists have carried out much research on this, and MagNet, Feature Squeezing and Defense-GAN are excellent research achievements. In this paper, we propose to improve MagNet. By proposing a new network structure and integrating ensemble learning technology, experiments show that this MagNet combined with ensemble learning technology has many advantages over the original MagNet. From the perspective of training time, the training time required by MagNet based on ensemble learning is reduced by half compared with the original MagNet. From the perspective of defense capability, Under the condition that the training time is sufficient and long, there is little difference between their defense capabilities. Under the condition that the training time is limited, MagNet based on ensemble learning is much better than the original MagNet. Similarly, according to this experimental idea, this paper conducts comparative experiments with Feature Squeezing algorithm and Defense-GAN algorithm from the perspective of training time and defense capability and finds that MagNet based on ensemble learning also has advantages.

Citation Download Citation

Zebin Zhuang "Ensemble MagNet:A fast training network against adversarial examples", Proc. SPIE 12635, Second International Conference on Algorithms, Microchips, and Network Applications (AMNA 2023), 126351L (8 May 2023); https://doi.org/10.1117/12.2679119

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
9 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Education and training

Defense and security

Gallium nitride

Neural networks

Adversarial training

Detection and tracking algorithms

Data modeling

Show All Keywords

Keywords/Phrases

Search In:

Publication Years