paper-with-me

Papers

Better Generalization with Adaptive Adversarial Training

2019-05-28 · Amit Despande, Sandesh Kamath, K V Subrahmanyam

An effective method to obtain an adversarial robust network is to train the network with adversarially perturbed samples. Perturbing all the samples adversarially has shown to increase the robustness of the networks significantly, but in turn affecting the generalization of the network to unperturbed points. We propose an adaptive training method which aims to perturb only a portion of the training samples which aids not only adversarial robustness but also better generalization as compared to perturbing all the training samples. This method is also faster than perturbing the entire training set.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial Robustness

Similar Papers 제목 키워드 기반

ASAT: Adaptively Scaled Adversarial Training in Time Series

2021-08-20 · Zhiyuan Zhang, Wei Li, Ruihan Bao, Keiko Harimoto 외

Adversarial training is a method for enhancing neural networks to improve the robustness against adversarial examples. Besides the security concerns of potential adversarial examples, adversarial training can also improv…

Adversarial RobustnessTime SeriesTime Series Analysis

Dynamic Perturbation-Adaptive Adversarial Training on Medical Image Classification

2024-03-11 · Shuai Li, Xiaoguang Ma, Shancheng Jiang, Lu Meng

Remarkable successes were made in Medical Image Classification (MIC) recently, mainly due to wide applications of convolutional neural networks (CNNs). However, adversarial examples (AEs) exhibited imperceptible similari…

image-classificationImage ClassificationMedical Image Classification

CAT: Customized Adversarial Training for Improved Robustness

2020-02-17 · Minhao Cheng, Qi Lei, Pin-Yu Chen, Inderjit Dhillon 외

Adversarial training has become one of the most effective methods for improving robustness of neural networks. However, it often suffers from poor generalization on both clean and perturbed data. In this paper, we propos…

Adaptive adversarial training method for improving multi-scale GAN based on generalization bound theory

2022-11-30 · Jing Tang, Bo Tao, Zeyu Gong, Zhouping Yin

In recent years, multi-scale generative adversarial networks (GANs) have been proposed to build generalized image processing models based on single sample. Constraining on the sample size, multi-scale GANs have much diff…

Image ManipulationImage Super-ResolutionSuper-Resolution

Improved OOD Generalization via Adversarial Training and Pre-training

2021-05-24 · Mingyang Yi, Lu Hou, Jiacheng Sun, Lifeng Shang 외

Recently, learning a model that generalizes well on out-of-distribution (OOD) data has attracted great attention in the machine learning community. In this paper, after defining OOD generalization via Wasserstein distanc…

image-classificationImage ClassificationNatural Language Understanding