Search engine for discovering works of Art, research articles, and books related to Art and Culture
ShareThis
Javascript must be enabled to continue!

Robust Weight Perturbation for Adversarial Training

View through CrossRef
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 the classification loss on adversarial examples. Adversarial weight perturbation helps reduce the robust generalization gap; however, it also undermines the robustness improvement. A criterion that regulates the weight perturbation is therefore crucial for adversarial training. In this paper, we propose such a criterion, namely Loss Stationary Condition (LSC) for constrained perturbation. With LSC, we find that it is essential to conduct weight perturbation on adversarial data with small classification loss to eliminate robust overfitting. Weight perturbation on adversarial data with large classification loss is not necessary and may even lead to poor robustness. Based on these observations, we propose a robust perturbation strategy to constrain the extent of weight perturbation. The perturbation strategy prevents deep networks from overfitting while avoiding the side effect of excessive weight perturbation, significantly improving the robustness of adversarial training. Extensive experiments demonstrate the superiority of the proposed method over the state-of-the-art adversarial training methods.
Title: Robust Weight Perturbation for Adversarial Training
Description:
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 the classification loss on adversarial examples.
Adversarial weight perturbation helps reduce the robust generalization gap; however, it also undermines the robustness improvement.
A criterion that regulates the weight perturbation is therefore crucial for adversarial training.
In this paper, we propose such a criterion, namely Loss Stationary Condition (LSC) for constrained perturbation.
With LSC, we find that it is essential to conduct weight perturbation on adversarial data with small classification loss to eliminate robust overfitting.
Weight perturbation on adversarial data with large classification loss is not necessary and may even lead to poor robustness.
Based on these observations, we propose a robust perturbation strategy to constrain the extent of weight perturbation.
The perturbation strategy prevents deep networks from overfitting while avoiding the side effect of excessive weight perturbation, significantly improving the robustness of adversarial training.
Extensive experiments demonstrate the superiority of the proposed method over the state-of-the-art adversarial training methods.

Related Results

[RETRACTED] Prima Weight Loss Dragons Den UK v1
[RETRACTED] Prima Weight Loss Dragons Den UK v1
[RETRACTED]Prima Weight Loss Dragons Den UK :-Obesity is a not kidding medical issue brought about by devouring an excessive amount of fat, eating terrible food sources, and practi...
[RETRACTED] Prima Weight Loss Dragons Den UK v1
[RETRACTED] Prima Weight Loss Dragons Den UK v1
[RETRACTED]Prima Weight Loss Dragons Den UK :-Obesity is a not kidding medical issue brought about by devouring an excessive amount of fat, eating terrible food sources, and practi...
Improving Adversarial Robustness via Finding Flat Minimum of the Weight Loss Landscape
Improving Adversarial Robustness via Finding Flat Minimum of the Weight Loss Landscape
<p>Recent studies have shown that robust overfitting and robust generalization gap are a major trouble in adversarial training of deep neural networks. These interesting prob...
ProDef-MDS: A Proactive Defense Mechanism Protecting Malware Detection Systems from Adversarial Attacks
ProDef-MDS: A Proactive Defense Mechanism Protecting Malware Detection Systems from Adversarial Attacks
Malware threatens cybersecurity by enabling data theft, unauthorized access, and extortion. Traditional malware detection systems (MDS) struggle with the increasing volume and comp...
Mixed Perturbation: Generating Directionally Diverse Perturbations for Adversarial Training
Mixed Perturbation: Generating Directionally Diverse Perturbations for Adversarial Training
The adversarial vulnerability of deep learning models is a critical issue that must be addressed to ensure the safe commercialization of AI technologies. Although numerous studies ...
Enhancing Adversarial Robustness through Stable Adversarial Training
Enhancing Adversarial Robustness through Stable Adversarial Training
Deep neural network models are vulnerable to attacks from adversarial methods, such as gradient attacks. Evening small perturbations can cause significant differences in their pred...
Efficient Defense Against First Order Adversarial Attacks on Convolutional Neural Networks
Efficient Defense Against First Order Adversarial Attacks on Convolutional Neural Networks
Machine learning models, especially neural networks, are vulnerable to adversarial attacks, where inputs are purposefully altered to induce incorrect predictions. These adversarial...
Adversarial Training and Robustness in Machine Learning Frameworks
Adversarial Training and Robustness in Machine Learning Frameworks
In the realm of machine learning, ensuring robustness against adversarial attacks is increasingly crucial. Adversarial training has emerged as a prominent strategy to fortify model...

Back to Top