TechRxiv
Adversarial_Attack_using_Neural_Image_Modification - Jan 17.pdf (12.45 MB)
Download file

Adversarial Attack using Neural Image Modification

Download (12.45 MB)
preprint
posted on 25.01.2022, 13:37 authored by Jandrik LanaJandrik Lana
In order to help development into analyzing the characteristics of adversarial sample generation in artificial neural networks, this work proposes a framework for an adversarial attack that utilizes neural image modification to generate an adversarial sample. This method proves to be effective in reducing a target network’s accuracy in both untargeted and targeted attacks with good success rates. This method also shows some effectiveness against defensive distillation, but not transferrable between multiple models.

History

Email Address of Submitting Author

jandrikrlana@gmail.com

ORCID of Submitting Author

0000-0001-7819-566X

Submitting Author's Institution

Quezon City Science High School

Submitting Author's Country

Philippines

Usage metrics

Licence

Exports