paper-with-me

홈 › Papers

APE-GAN: Adversarial Perturbation Elimination with GAN

2017-07-18 · Shiwei Shen, Guoqing Jin, Ke Gao, Yongdong Zhang

Although neural networks could achieve state-of-the-art performance while recongnizing images, they often suffer a tremendous defeat from adversarial examples--inputs generated by utilizing imperceptible but intentional perturbation to clean samples from the datasets. How to defense against adversarial examples is an important problem which is well worth researching. So far, very few methods have provided a significant defense to adversarial examples. In this paper, a novel idea is proposed and an effective framework based Generative Adversarial Nets named APE-GAN is implemented to defense against the adversarial examples. The experimental results on three benchmark datasets including MNIST, CIFAR10 and ImageNet indicate that APE-GAN is effective to resist adversarial examples generated from five attacks.

📄 PDF Abstract BibTeX arXiv:1707.05474

Code (3)

shenqixiaojiang/APE-GAN 공식 구현 tf
carlini/APE-GAN tf
owruby/ape-gan pytorch

Similar Papers 제목 키워드 기반

MAPE: Defending Against Transferable Adversarial Attacks Using Multi-Source Adversarial Perturbations Elimination

2026-06-30 · Xinlei Liu, Jichao Xie, Tao Hu, Peng Yi 외 arxiv

Neural networks are vulnerable to meticulously crafted adversarial examples, leading to high-confidence misclassifications in image classification tasks. Due to their consistency with regular input patterns and the absen…

Image Classification

Boosting the Transferability of Adversarial Attacks with Global Momentum Initialization

2022-11-21 · Jiafeng Wang, Zhaoyu Chen, Kaixun Jiang, Dingkang Yang 외

Deep Neural Networks (DNNs) are vulnerable to adversarial examples, which are crafted by adding human-imperceptible perturbations to the benign inputs. Simultaneously, adversarial examples exhibit transferability across …

A Robust Phased Elimination Algorithm for Corruption-Tolerant Gaussian Process Bandits

2022-02-03 · Ilija Bogunovic, Zihan Li, Andreas Krause, Jonathan Scarlett

We consider the sequential optimization of an unknown, continuous, and expensive to evaluate reward function, from noisy and adversarially corrupted observed rewards. When the corruption attacks are subject to a suitable…

Adversarial Training: embedding adversarial perturbations into the parameter space of a neural network to build a robust system

2019-10-09 · Shixian Wen, Laurent Itti

Adversarial training, in which a network is trained on both adversarial and clean examples, is one of the most trusted defense methods against adversarial attacks. However, there are three major practical difficulties in…

Diversity

Robust Weight Perturbation for Adversarial Training

2022-05-30 · Chaojian Yu, Bo Han, Mingming Gong, Li Shen 외

Overfitting widely exists in adversarial robust training of deep networks. An effective remedy is adversarial weight perturbation, which injects the worst-case weight perturbation during network training by maximizing th…

Classification