Accès chercheur

EEDIS Laboratory

Evolutionary Engineering


Distributed Information Systems

Réseaux et Communication

Sécurité et Multimédia

Ingénierie des Connaissances

Data Mining & Web Intelligent

Interopérabilité des Systèmes d’information
& Bases de données

Développement Orienté Service

Detect and defense against adversarial examples in deep learning using natural scene statistics and adaptive denoising

Auteurs: » Kherchouche Anouar
» Hamidouche Wassim
Type : Chapitre de Livre
Edition : Springer London ISBN:
Lien : »
Publié le : 21-07-2021

Despite theenormous performance of deep neural networks (DNNs), recent studies have showntheir vulnerability to adversarial examples (AEs), i.e., carefully perturbedinputs designed to fool the targeted DNN. Currently, the literature is richwith many effective attacks to craft such AEs. Meanwhile, many defensestrategies have been developed to mitigate this vulnerability. However, theselatter showed their effectiveness against specific attacks and does notgeneralize well to different attacks. In this paper, we propose a framework fordefending DNN classifier against adversarial samples. The proposed method isbased on a two-stage framework involving a separate detector and a denoisingblock. The detector aims to detect AEs by characterizing them through the useof natural scene statistic (NSS), where we demonstrate that these statisticalfeatures are altered by the presence of adversarial â€¦

Tous droits réservés - © 2019 EEDIS Laboratory