QR code

GReAT: A Graph Regularized Adversarial Training Method

This paper presents GReAT (Graph Regularized Adversarial Training), a novel regularization method designed to enhance the robust classification performance of deep learning models. Adversarial examples, characterized by subtle perturbations that can mislead models, pose a significant challenge in ma...

Volledige beschrijving

Bewaard in:
Hoofdauteurs: Samet Bayram, Kenneth Barner
Formaat: Artigo
Taal:Inglês
Gepubliceerd in: IEEE 2024-01-01
Reeks:IEEE Access
Onderwerpen:
Adversarial examples
adversarial learning
adversarial training
graph regularization
image classification
semi-supervised learning
Online toegang:https://ieeexplore.ieee.org/document/10516321/
Tags: Voeg label toe
Geen labels, Wees de eerste die dit record labelt!

Gelijkaardige items