Adversarial Margin Maximization Networks

11/14/2019
by   Ziang Yan, et al.
0

The tremendous recent success of deep neural networks (DNNs) has sparked a surge of interest in understanding their predictive ability. Unlike the human visual system which is able to generalize robustly and learn with little supervision, DNNs normally require a massive amount of data to learn new concepts. In addition, research works also show that DNNs are vulnerable to adversarial examples-maliciously generated images which seem perceptually similar to the natural ones but are actually formed to fool learning models, which means the models have problem generalizing to unseen data with certain type of distortions. In this paper, we analyze the generalization ability of DNNs comprehensively and attempt to improve it from a geometric point of view. We propose adversarial margin maximization (AMM), a learning-based regularization which exploits an adversarial perturbation as a proxy. It encourages a large margin in the input space, just like the support vector machines. With a differentiable formulation of the perturbation, we train the regularized DNNs simply through back-propagation in an end-to-end manner. Experimental results on various datasets (including MNIST, CIFAR-10/100, SVHN and ImageNet) and different DNN architectures demonstrate the superiority of our method over previous state-of-the-arts. Code and models for reproducing our results will be made publicly available.

READ FULL TEXT
research
02/23/2018

DeepDefense: Training Deep Neural Networks with Improved Robustness

Despite the efficacy on a variety of computer vision tasks, deep neural ...
research
03/25/2021

Recent Advances in Large Margin Learning

This paper serves as a survey of recent advances in large margin trainin...
research
06/30/2022

Detecting and Recovering Adversarial Examples from Extracting Non-robust and Highly Predictive Adversarial Perturbations

Deep neural networks (DNNs) have been shown to be vulnerable against adv...
research
01/21/2019

Generating Textual Adversarial Examples for Deep Learning Models: A Survey

With the development of high computational devices, deep neural networks...
research
09/20/2019

Adversarial Learning with Margin-based Triplet Embedding Regularization

The Deep neural networks (DNNs) have achieved great success on a variety...
research
01/21/2020

Understanding Why Neural Networks Generalize Well Through GSNR of Parameters

As deep neural networks (DNNs) achieve tremendous success across many ap...
research
08/13/2019

Learning Credible Deep Neural Networks with Rationale Regularization

Recent explainability related studies have shown that state-of-the-art D...

Please sign up or login with your details

Forgot password? Click here to reset