Defense against adversarial attacks: robust and efficient compressed optimized neural networks

Defense against adversarial attacks: robust and efficient compressed optimized neural networks

Abstract In the ongoing battle against adversarial attacks, adopting a suitable strategy to enhance model efficiency, bolster resistance to adversarial threats, and ensure practical deployment is crucial. To achieve this goal, a novel four-component methodology is introduced. First, introducing a pi...

Full description

Bibliographic Details
Main Authors: Insaf Kraidia, Afifa Ghenai, Samir Brahim Belhaouari
Format: Article
Language:English
Published: Nature Portfolio 2024-03-01
Series:Scientific Reports
Subjects:
Adversarial attacks
Generative pre-trained transformer (GPT)
Compression
Multi expert
Online Access:https://doi.org/10.1038/s41598-024-56259-z

Internet

https://doi.org/10.1038/s41598-024-56259-z

Similar Items