Exploring CNN features in the context of adversarial robustness and human perception

Enzo Casamassima; Andrew Herbert; Cory Merkel

doi:10.1117/12.2594363

1 August 2021 Exploring CNN features in the context of adversarial robustness and human perception

Enzo Casamassima, Andrew Herbert, Cory Merkel

Proceedings Volume 11843, Applications of Machine Learning 2021; 1184313 (2021) https://doi.org/10.1117/12.2594363
Event: SPIE Optical Engineering + Applications, 2021, San Diego, California, United States

Conference Poster

Abstract

Recent studies in the field of adversarial machine learning have highlighted the poor robustness of convolutional neural networks (CNNs) to small, carefully crafted variations of the inputs. Previous work in this area has largely been focused on very small image perturbations and how these completely throw off the classifier output and cause CNNs to make high-confidence misclassifications while leaving the image visually unchanged for a human observer. These attacks modify individual pixels of each image and are unlikely to exist in a natural environment. More recent work has demonstrated that CNNs are also vulnerable to simple transformations of the input image, such as rotations and translations. These ‘natural’ transformations are much more likely to occur, either accidentally or intentionally, in a real-world scenario. In fact, humans experience and successfully recognize countless objects under these types of transformations every day. In this paper, we study the effect of these transformations on CNN accuracy when classifying 3D face-like objects (Greebles). Furthermore, we visualize the learned feature representations by CNNs and analyze how robust these learned representations are and how they compare to the human visual system. This work serves as a basis for future research into understanding the differences between CNN and human object recognition, particularly in the context of adversarial examples.

Citation Download Citation

Enzo Casamassima, Andrew Herbert, and Cory Merkel "Exploring CNN features in the context of adversarial robustness and human perception", Proc. SPIE 11843, Applications of Machine Learning 2021, 1184313 (1 August 2021); https://doi.org/10.1117/12.2594363

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