Defending Deep Neural Networks Against Backdoor Attack by Using De-Trigger Autoencoder

Defending Deep Neural Networks Against Backdoor Attack by Using De-Trigger Autoencoder

A backdoor attack is a method that causes misrecognition in a deep neural network by training it on additional data that have a specific trigger. The network will correctly recognize normal samples (which lack the specific trigger) as their proper classes but will misrecognize backdoor samples (whic...

Full description

Saved in:
Bibliographic Details
Main Author: Hyun Kwon
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Backdoor attack
defense method
deep neural network
de-trigger autoencoder
Online Access:https://ieeexplore.ieee.org/document/9579062/
Tags: Add Tag
No Tags, Be the first to tag this record!

Similar Items

Similar Items