First line of defense: A robust first layer mitigates adversarial attacks

TL;DR

This work demonstrates that a carefully designed first layer of the neural network can serve as an implicit adversarial noise filter (ANF) that achieves higher adversarial accuracies than existing natively robust architectures without AT and is competitive with adversarial-trained architectures across a wide range of datasets.

Abstract

Adversarial training (AT) incurs significant computational overhead, leading to growing interest in designing inherently robust architectures. We demonstrate that a carefully designed first layer of the neural network can serve as an implicit adversarial noise filter (ANF). This filter is created using a combination of large kernel size, increased convolution filters, and a maxpool operation. We show that integrating this filter as the first layer in architectures such as ResNet, VGG, and EfficientNet results in adversarially robust networks. Our approach achieves higher adversarial accuracies than existing natively robust architectures without AT and is competitive with adversarial-trained architectures across a wide range of datasets. Supporting our findings, we show that (a) the decision regions for our method have better margins, (b) the visualized loss surfaces are smoother, (c) the modified peak signal-to-noise ratio (mPSNR) values at the output of the ANF are higher, (d) high-frequency components are more attenuated, and (e) architectures incorporating ANF exhibit better denoising in Gaussian noise compared to baseline architectures. Code for all our experiments are available at \url{https://github.com/janani-suresh-97/first-line-defence.git}.

Figures (9)

• Figure 1: ANF with ResNet20
• Figure 2: Visualization of the decision regions
• Figure 3: Visualization of 3D loss surface (a,c) and contour plots (b, d) with adversarial samples.
• Figure 4: ANF implemented with VGG architecture, showcasing modified feature dimensions.
• Figure 5: Visualization of the decision regions