ARGAN: Adversarially Robust Generative Adversarial Networks for Deep Neural Networks Against Adversarial Examples

ARGAN: Adversarially Robust Generative Adversarial Networks for Deep Neural Networks Against Adversarial Examples

An adversarial example, which is an input instance with small, intentional feature perturbations to machine learning models, represents a concrete problem in Artificial intelligence safety. As an emerging defense method to defend against adversarial examples, generative adversarial networks-based de...

Cijeli opis

Bibliografski detalji
Glavni autori: Seok-Hwan Choi, Jin-Myeong Shin, Peng Liu, Yoon-Ho Choi
Format: Članak
Jezik:English
Izdano: IEEE 2022-01-01
Serija:IEEE Access
Teme:
Adversarial examples
adversarial perturbation
deep neural networks (DNNs)
security
Online pristup:https://ieeexplore.ieee.org/document/9737142/

Internet

https://ieeexplore.ieee.org/document/9737142/

Slični predmeti