Adversarial attacks in deep neural networks: an explanation through multi-level interactions and the use of Shapley value

YuMing Ma; Hao Zhang

doi:10.1117/12.2679076

25 May 2023 Adversarial attacks in deep neural networks: an explanation through multi-level interactions and the use of Shapley value

YuMing Ma, Hao Zhang

Author Affiliations +

Proceedings Volume 12712, International Conference on Cloud Computing, Performance Computing, and Deep Learning (CCPCDL 2023); 127121P (2023) https://doi.org/10.1117/12.2679076
Event: International Conference on Cloud Computing, Performance Computing, and Deep Learning (CCPCDL 2023), 2023, Huzhou, China

Abstract

The field of adversarial robustness has gained significant attention in recent years due to the advancements in deep learning and the increasing complexity of tasks performed by deep neural networks. Despite this progress, the underlying mechanism behind the performance of these networks in the face of adversarial attacks remains poorly understood. The existing explanations are largely based on intuition. This study provides a comprehensive explanation of various adversarial attacks by examining the multi-level interactions between input variables in deep neural networks. Utilizing the Shapley value, we believe that these attacks primarily target high-level interactions to mislead the network. The study’s effectiveness is demonstrated through application to re-identification models. Additionally, possible reasons for minor variations in results are discussed.

Citation Download Citation

YuMing Ma and Hao Zhang "Adversarial attacks in deep neural networks: an explanation through multi-level interactions and the use of Shapley value", Proc. SPIE 12712, International Conference on Cloud Computing, Performance Computing, and Deep Learning (CCPCDL 2023), 127121P (25 May 2023); https://doi.org/10.1117/12.2679076

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
5 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Neural networks

Education and training

Image classification

Reflection

Machine learning

Network security

Visualization

Show All Keywords

Keywords/Phrases

Search In:

Publication Years