An Information Geometric Perspective to Adversarial Attacks and Defenses
Authors:
- 18 July 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
Abstract
Deep learning models have achieved state-of-the-art accuracy in complex tasks, sometimes outperforming human-level accuracy. Yet, they suffer from vulnerabilities known as adversarial attacks, which are imperceptible input perturbations that fool the models on inputs that were originally classified correctly. The adversarial problem remains poorly understood and commonly thought to be an inherent weakness of deep learning models. We argue that understanding and alleviating the adversarial phenomenon may require us to go beyond the Euclidean view and consider the relationship between the input and output spaces as a statistical manifold with the Fisher Information as its Riemannian metric. Under this information geometric view, the optimal attack is constructed as the direction corresponding to the highest eigenvalue of the Fisher Information Matrix - called the Fisher spectral attack. We show that an orthogonal transformation of the data cleverly alters its manifold by keeping the highest eigenvalue but changing the optimal direction of attack; thus deceiving the attacker into adopting the wrong direction. We demonstrate the defensive capabilities of the proposed orthogonal scheme - against the Fisher spectral attack and the popular fast gradient sign method - on standard networks, e.g., LeNet and MobileNetV2 for benchmark data sets, MNIST and CIFAR-10.Keywords
This publication has 9 references indexed in Scilit:
- Inspecting adversarial examples using the fisher informationNeurocomputing, 2020
- MobileNetV2: Inverted Residuals and Linear Bottlenecks2018
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision ApplicationsarXiv, 2017
- Adversarial Examples for Evaluating Reading Comprehension Systems2017
- Scheduled denoising autoencodersarXiv, 2015
- The MNIST Database of Handwritten Digit Images for Machine Learning Research [Best of the Web]IEEE Signal Processing Magazine, 2012
- Methods of Information Geometry2007
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- Multilayer feedforward networks are universal approximatorsNeural Networks, 1989