Adversarial attacks for machine learning denoisers and how to resist them

Saiyam B. Jain; Shao Zongru; Sachin K. T. Veettil; Michael Hecht

doi:10.1117/12.2632954

3 October 2022 Adversarial attacks for machine learning denoisers and how to resist them

Saiyam B. Jain, Shao Zongru, Sachin K. T. Veettil, Michael Hecht

Proceedings Volume 12204, Emerging Topics in Artificial Intelligence (ETAI) 2022; 1220402 (2022) https://doi.org/10.1117/12.2632954
Event: SPIE Nanoscience + Engineering, 2022, San Diego, California, United States

Abstract

Adversarial attacks rely on the instability phenomenon appearing in general for all inverse problems, e.g., image classification and reconstruction, independently of the computational scheme or method used to solve the problem. We mathematically prove and empirically show that machine learning denoisers (MLD) are not excluded. That is to prove the existence of adversarial attacks given by noise patterns making the MLD run into instability, i.e., the MLD increases the noise instead of decreasing it. We further demonstrate that adversarial retraining or classic filtering do not provide an exit strategy for this dilemma. Instead, we show that adversarial attacks can be inferred by polynomial regression. Removing the underlying inferred polynomial distribution from the total noise distribution delivers an efficient technique yielding robust MLDs that make consistent computer vision tasks such as image segmentation or classification more reliable.

Citation Download Citation

Saiyam B. Jain, Shao Zongru, Sachin K. T. Veettil, and Michael Hecht "Adversarial attacks for machine learning denoisers and how to resist them", Proc. SPIE 12204, Emerging Topics in Artificial Intelligence (ETAI) 2022, 1220402 (3 October 2022); https://doi.org/10.1117/12.2632954

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