Architectural Resilience to Foreground-and-Background Adversarial Noise

03/23/2020
by   Carl Cheng, et al.
4

Adversarial attacks in the form of imperceptible perturbations of normal images have been extensively studied, and for every new defense methodology created, multiple adversarial attacks are found to counteract it. In particular, a popular style of attack, exemplified in recent years by DeepFool and Carlini-Wagner, relies solely on white-box scenarios in which full access to the predictive model and its weights are required. In this work, we instead propose distinct model-agnostic benchmark perturbations of images in order to investigate the resilience and robustness of different network architectures. Results empirically determine that increasing depth within most types of Convolutional Neural Networks typically improves model resilience towards general attacks, with improvement steadily decreasing as the model becomes deeper. Additionally, we find that a notable difference in adversarial robustness exists between residual architectures with skip connections and non-residual architectures of similar complexity. Our findings provide direction for future understanding of residual connections and depth on network robustness.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/07/2019

JumpReLU: A Retrofit Defense Strategy for Adversarial Attacks

It has been demonstrated that very simple attacks can fool highly-sophis...
research
08/21/2022

MockingBERT: A Method for Retroactively Adding Resilience to NLP Models

Protecting NLP models against misspellings whether accidental or adversa...
research
12/09/2018

Feature Denoising for Improving Adversarial Robustness

Adversarial attacks to image classification systems present challenges t...
research
11/16/2021

Robustness of Bayesian Neural Networks to White-Box Adversarial Attacks

Bayesian Neural Networks (BNNs), unlike Traditional Neural Networks (TNN...
research
11/29/2020

Architectural Adversarial Robustness: The Case for Deep Pursuit

Despite their unmatched performance, deep neural networks remain suscept...
research
06/10/2020

Interpolation between Residual and Non-Residual Networks

Although ordinary differential equations (ODEs) provide insights for des...
research
06/24/2018

SSIMLayer: Towards Robust Deep Representation Learning via Nonlinear Structural Similarity

Deeper convolutional neural networks provide more capacity to approximat...

Please sign up or login with your details

Forgot password? Click here to reset