Frequency Centric Defense Mechanisms against Adversarial Examples

2021-10-26 · Sanket B. Shah, Param Raval, Harin Khakhi, Mehul S. Raval

Adversarial example (AE) aims at fooling a Convolution Neural Network by introducing small perturbations in the input image.The proposed work uses the magnitude and phase of the Fourier Spectrum and the entropy of the image to defend against AE. We demonstrate the defense in two ways: by training an adversarial detector and denoising the adversarial effect. Experiments were conducted on the low-resolution CIFAR-10 and high-resolution ImageNet datasets. The adversarial detector has 99% accuracy for FGSM and PGD attacks on the CIFAR-10 dataset. However, the detection accuracy falls to 50% for sophisticated DeepFool and Carlini & Wagner attacks on ImageNet. We overcome the limitation by using autoencoder and show that 70% of AEs are correctly classified after denoising.

📄 PDF Abstract BibTeX arXiv:2110.13935

Code (0)

등록된 구현이 없습니다.

Tasks

Denoising

Methods 이 논문이 사용한 방법론

AE An autoencoder is a type of artificial neural network used to learn efficient data codings in an unsupervised manner. The aim of an autoencoder is to learn a representation…

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Mitigation of Adversarial Examples in RF Deep Classifiers Utilizing AutoEncoder Pre-training

2019-02-16 · Silvija Kokalj-Filipovic, Rob Miller, Nicholas Chang, Chi Leung Lau

Adversarial examples in machine learning for images are widely publicized and explored. Illustrations of misclassifications caused by slightly perturbed inputs are abundant and commonly known (e.g., a picture of panda im…

Deep Learning

Defending against Patch-Based and Texture-Based Adversarial Attacks with Spectral Decomposition

2026-04-12 · Wei Zhang, Xinyu Chang, Xiao Li, Yiming Zhu 외 arxiv

Adversarial examples present significant challenges to the security of Deep Neural Network (DNN) applications. Specifically, there are patch-based and texture-based attacks that are usually used to craft physical-world a…

TensorShield: Tensor-based Defense Against Adversarial Attacks on Images

2020-02-18 · Negin Entezari, Evangelos E. Papalexakis

Recent studies have demonstrated that machine learning approaches like deep neural networks (DNNs) are easily fooled by adversarial attacks. Subtle and imperceptible perturbations of the data are able to change the resul…

BIG-bench Machine Learning image-classification Image Classification Tensor Decomposition

Adversarial Examples in RF Deep Learning: Detection of the Attack and its Physical Robustness

2019-02-16 · Silvija Kokalj-Filipovic, Rob Miller

While research on adversarial examples in machine learning for images has been prolific, similar attacks on deep learning (DL) for radio frequency (RF) signals and their mitigation strategies are scarcely addressed in th…

Robust Neural Networks using Randomized Adversarial Training

2019-03-25 · Alexandre Araujo, Laurent Meunier, Rafael Pinot, Benjamin Negrevergne

This paper tackles the problem of defending a neural network against adversarial attacks crafted with different norms (in particular $\ell_\infty$ and $\ell_2$ bounded adversarial examples). It has been observed that def…