Support samples guided adversarial generalization

En Yang; Tong Sun; Jun Liu

doi:10.1117/12.2667635

22 February 2023 Support samples guided adversarial generalization

En Yang, Tong Sun, Jun Liu

Proceedings Volume 12587, Third International Seminar on Artificial Intelligence, Networking, and Information Technology (AINIT 2022); 125870S (2023) https://doi.org/10.1117/12.2667635
Event: Third International Seminar on Artificial Intelligence, Networking, and Information Technology (AINIT 2022), 2022, Shanghai, China

Abstract

Adversarial training proves to be the most effective measure to classify adversarial perturbation, which is imperceptible but can drastically alter the output of the classifier. We review various theories behind the relationship between generalization gap and adversarial robustness and then raise the question: is it the input near the decision boundary that provides guidance for the classifier to learn the ideal decision boundary and therefore yield a more desired outcome? We provide quantitative confirmation that the expected required sample size correlates favorably with sample distance and further investigate the relationship between the robust classification error and the expected distance from the decision boundary to samples. Experimental results reveal that applying the data near the decision boundary as training sets can significantly promote adversarial generalization, which keeps consistence with the main conjectures presented in this work.

Citation Download Citation

En Yang, Tong Sun, and Jun Liu "Support samples guided adversarial generalization", Proc. SPIE 12587, Third International Seminar on Artificial Intelligence, Networking, and Information Technology (AINIT 2022), 125870S (22 February 2023); https://doi.org/10.1117/12.2667635

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