CriPI: an efficient critical pixels identification algorithm for fast one-pixel attacks

Wei Quan; Deeraj Nagothu; Nihal Poredi; Yu Chen

doi:10.1117/12.2581377

12 April 2021 CriPI: an efficient critical pixels identification algorithm for fast one-pixel attacks

Wei Quan, Deeraj Nagothu, Nihal Poredi, Yu Chen

Author Affiliations +

Proceedings Volume 11755, Sensors and Systems for Space Applications XIV; 117550M (2021) https://doi.org/10.1117/12.2581377
Event: SPIE Defense + Commercial Sensing, 2021, Online Only

Abstract

Deep neural networks (DNN) have been studied intensively in recent years, leading to many practical applications. However, there are also concerns about the security problems and vulnerabilities of DNN. Studies on adversarial network development have shown that relatively more minor perturbations can impact the DNN performance and manipulate its outcome. The impacts of adversarial perturbations have led to the development of advanced techniques for generating image-level perturbations. Once embedded in a clean image, these perturbations are not perceptible to human eyes and fool a well-trained deep learning (DL) convolutional neural network (CNN) classifier. This work introduces a new Critical-Pixel Iterative (CriPI) algorithm after a thorough study on critical pixels’ characteristics. The proposed CriPI algorithm can identify the critical pixels and generate one-pixel attack perturbations with a much higher efficiency. Compared to a one-pixel attack benchmark algorithm, the CriPI algorithm significantly reduces the time delay of the attack from seven minutes to one minute with similar success rates.

Conference Presentation

Citation Download Citation

Wei Quan, Deeraj Nagothu, Nihal Poredi, and Yu Chen "CriPI: an efficient critical pixels identification algorithm for fast one-pixel attacks", Proc. SPIE 11755, Sensors and Systems for Space Applications XIV, 117550M (12 April 2021); https://doi.org/10.1117/12.2581377

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