Automated Segmentation to Make Hidden Trigger Backdoor Attacks Robust against Deep Neural Networks

Automated Segmentation to Make Hidden Trigger Backdoor Attacks Robust against Deep Neural Networks

The successful outcomes of deep learning (DL) algorithms in diverse fields have prompted researchers to consider backdoor attacks on DL models to defend them in practical applications. Adversarial examples could deceive a safety-critical system, which could lead to hazardous situations. To cope with...

Full description

Bibliographic Details
Main Authors: Saqib Ali, Sana Ashraf, Muhammad Sohaib Yousaf, Shazia Riaz, Guojun Wang
Format: Article
Language:English
Published: MDPI AG 2023-04-01
Series:Applied Sciences
Subjects:
backdoor attacks
alternate triggers
data poisoning
adversarial examples
deep learning models
Online Access:https://www.mdpi.com/2076-3417/13/7/4599

Internet

https://www.mdpi.com/2076-3417/13/7/4599

Similar Items