paper-with-me

홈 › Papers

Countering Adversarial Images using Input Transformations

2017-10-31 · ICLR 2018 1 · Chuan Guo, Mayank Rana, Moustapha Cisse, Laurens van der Maaten

This paper investigates strategies that defend against adversarial-example attacks on image-classification systems by transforming the inputs before feeding them to the system. Specifically, we study applying image transformations such as bit-depth reduction, JPEG compression, total variance minimization, and image quilting before feeding the image to a convolutional network classifier. Our experiments on ImageNet show that total variance minimization and image quilting are very effective defenses in practice, in particular, when the network is trained on transformed images. The strength of those defenses lies in their non-differentiable nature and their inherent randomness, which makes it difficult for an adversary to circumvent the defenses. Our best defense eliminates 60% of strong gray-box and 90% of strong black-box attacks by a variety of major attack methods

📄 PDF Abstract BibTeX arXiv:1711.00117

Code (1)

facebookresearch/adversarial_image_defenses 공식 구현 pytorch

Tasks

Adversarial DefenseGeneral Classificationimage-classificationImage Classification

Similar Papers 제목 키워드 기반

Detecting Adversarial Examples by Input Transformations, Defense Perturbations, and Voting

2021-01-27 · Federico Nesti, Alessandro Biondi, Giorgio Buttazzo

Over the last few years, convolutional neural networks (CNNs) have proved to reach super-human performance in visual recognition tasks. However, CNNs can easily be fooled by adversarial examples, i.e., maliciously-crafte…

Adversarial Defense by Latent Style Transformations

2020-06-17 · Shuo Wang, Surya Nepal, Alsharif Abuadbba, Carsten Rudolph 외

Machine learning models have demonstrated vulnerability to adversarial attacks, more specifically misclassification of adversarial examples. In this paper, we investigate an attack-agnostic defense against adversarial at…

Adversarial Defense

Enhanced countering adversarial attacks via input denoising and feature restoring

2021-11-19 · Yanni Li, Wenhui Zhang, Jiawei Liu, Xiaoli Kou 외

Despite the fact that deep neural networks (DNNs) have achieved prominent performance in various applications, it is well known that DNNs are vulnerable to adversarial examples/samples (AEs) with imperceptible perturbati…

Adversarial AttackDenoising

Admix: Enhancing the Transferability of Adversarial Attacks

2021-01-31 · ICCV 2021 10 · Xiaosen Wang, Xuanran He, Jingdong Wang, Kun He

Deep neural networks are known to be extremely vulnerable to adversarial examples under white-box setting. Moreover, the malicious adversaries crafted on the surrogate (source) model often exhibit black-box transferabili…

Property-Preserving Hashing for $\ell_1$-Distance Predicates: Applications to Countering Adversarial Input Attacks

2025-04-23 · Hassan Asghar, Chenhan Zhang, Dali Kaafar

Perceptual hashing is used to detect whether an input image is similar to a reference image with a variety of security applications. Recently, they have been shown to succumb to adversarial input attacks which make small…