Design of adversarial targets: fooling deep ATR systems

Uche M. Osahor; Nasser M. Nasrabadi

doi:10.1117/12.2518945

14 May 2019 Design of adversarial targets: fooling deep ATR systems

Uche M. Osahor, Nasser M. Nasrabadi

Proceedings Volume 10988, Automatic Target Recognition XXIX; 109880F (2019) https://doi.org/10.1117/12.2518945
Event: SPIE Defense + Commercial Sensing, 2019, Baltimore, MD, United States

Abstract

Deep Convolutional Neural Networks (DCNN) have proven to be an exceptional tool for object recognition in various computer vision applications. However, recent findings have shown that such state of the art models can be easily deceived by inserting slight imperceptible perturbations to key pixels in the input image. In this paper, we focus on deceiving Automatic Target Recognition(ATR) classiers. These classiers are built to recognize specified targets in a scene and also simultaneously identify their class types. In our work, we explore the vulnerabilities of DCNN-based target classifiers. We demonstrate significant progress in developing infrared adversarial target by adding small perturbations to the input image such that the image perturbation cannot be easily detected. The algorithm is built to adapt to both targeted and non-targeted adversarial attacks. Our findings reveal promising results that reflect serious implications of adversarial attacks.

Conference Presentation

Citation Download Citation

Uche M. Osahor and Nasser M. Nasrabadi "Design of adversarial targets: fooling deep ATR systems", Proc. SPIE 10988, Automatic Target Recognition XXIX, 109880F (14 May 2019); https://doi.org/10.1117/12.2518945

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