Designing defensive techniques to handle adversarial attack on deep learning based model
PeerJ Computer Science · 08.03.2024 · 10 · e1868
DOI: 10.7717/peerj-cs.1868 ↗Kurz gefasst
Fachartikel in der Zeitschrift PeerJ Computer Science, online erschienen am 08.03.2024. Verfasst von Dhairya Vyas und 1 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Adversarial attacks pose a significant challenge to deep neural networks used in image classification systems. Although deep learning has achieved impressive success in various tasks, it can easily be deceived by adversarial patches created by adding subtle yet deliberate distortions to natural images. These attacks are designed to remain hidden from both human and computer-based classifiers. Considering this, we propose novel model designs that enhance adversarial strength with incorporating feature denoising blocks. Exclusively, proposed model utilizes Gaussian data augmentation (GDA) and spatial smoothing (SS) to denoise the features. These techniques are reasonable and can be mixed in a joint finding context to accomplish superior recognition levels versus adversarial assaults while also balancing other defenses. We tested the proposed approach on the ImageNet and CIFAR-10 datasets using 10-iteration projected gradient descent (PGD), fast gradient sign method (FGSM), and DeepFool attacks. The proposed method achieved an accuracy of 95.62% in under four minutes, which is highly competitive compared to existing approaches. We also conducted a comparative analysis with existing methods.
Zitieren
APA
Vyas, D., & Kapadia, V. V. (2024). Designing defensive techniques to handle adversarial attack on deep learning based model. PeerJ Computer Science, 10, e1868. https://doi.org/10.7717/peerj-cs.1868
Vancouver
Vyas D, Kapadia VV. Designing defensive techniques to handle adversarial attack on deep learning based model. PeerJ Computer Science. 2024;10:e1868. doi:10.7717/peerj-cs.1868
BibTeX
@article{Vyas2024,
author = {Vyas, Dhairya and Kapadia, Viral V.},
title = {Designing defensive techniques to handle adversarial attack on deep learning based model},
journal = {PeerJ Computer Science},
year = {2024},
volume = {10},
pages = {e1868},
doi = {10.7717/peerj-cs.1868}
}
EUVIMED