activity
20192021
most citedDetect and Defense Against Adversarial Examples in Deep Learning using Natural Scene Statistics and Adaptive Denoising

1 citations · 1 across the 5 of their papers we have counts for

collaborators
Showing cs.CVShow all

2 papers · 1 filter

cs.CV2022★ 2 cited

Evaluation of Pre-Trained CNN Models for Geographic Fake Image Detection

Sid Ahmed Fezza, Mohammed Yasser Ouis, Bachir Kaddar +2

Thanks to the remarkable advances in generative adversarial networks (GANs), it is becoming increasingly easy to generate/manipulate images. The existing works have mainly focused…

cs.CV2021★ 1 cited

Detect and Defense Against Adversarial Examples in Deep Learning using Natural Scene Statistics and Adaptive Denoising

Anouar Kherchouche, Sid Ahmed Fezza, Wassim Hamidouche

Despite the enormous performance of deepneural networks (DNNs), recent studies have shown theirvulnerability to adversarial examples (AEs), i.e., care-fully perturbed inputs design…