Using image quality metrics to identify adversarial imagery for deep learning networks

Josh Harguess; Jeremy Miclat; Julian Raheema

doi:10.1117/12.2263584

1 May 2017 Using image quality metrics to identify adversarial imagery for deep learning networks

Josh Harguess, Jeremy Miclat, Julian Raheema

Proceedings Volume 10199, Geospatial Informatics, Fusion, and Motion Video Analytics VII; 1019907 (2017) https://doi.org/10.1117/12.2263584
Event: SPIE Defense + Security, 2017, Anaheim, CA, United States

Abstract

Deep learning has continued to gain momentum in applications across many critical areas of research in computer vision and machine learning. In particular, deep learning networks have had much success in image classification, especially when training data are abundantly available, as is the case with the ImageNet project. However, several researchers have exposed potential vulnerabilities of these networks to carefully crafted adversarial imagery. Additionally, researchers have shown the sensitivity of these networks to some types of noise and distortion. In this paper, we investigate the use of no-reference image quality metrics to identify adversarial imagery and images of poor quality that could potentially fool a deep learning network or dramatically reduce its accuracy. Results are shown on several adversarial image databases with comparisons to popular image classification databases.

Conference Presentation

Citation Download Citation

Josh Harguess, Jeremy Miclat, and Julian Raheema "Using image quality metrics to identify adversarial imagery for deep learning networks", Proc. SPIE 10199, Geospatial Informatics, Fusion, and Motion Video Analytics VII, 1019907 (1 May 2017); https://doi.org/10.1117/12.2263584

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