Adversarial Machine Learning: Attacks, Defenses, and the Path Towards Trustworthy AI
International Journal of Innovative Science and Research Technology · 01.07.2026 · 1962
DOI: 10.38124/ijisrt/26jun1631 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Innovative Science and Research Technology, online erschienen am 01.07.2026. Verfasst von Jieyao Pang. Die Arbeit nennt 18 Literaturangaben.
Abstract (Originalsprache)
Deep neural networks achieve strong performance on perception tasks but remain vulnerable to adversarial examples—imperceptibly perturbed inputs that induce confident misclassification. This dissertation reviews the adversarial attack–defence landscape and reports CIFAR-10 experiments using ResNet-18. It compares a standard baseline, a PGDadversarially trained model, and a model obtained from RobustBench under FGSM, PGD-20, and AutoAttack.
Zitieren
APA
Pang, J. (2026). Adversarial Machine Learning: Attacks, Defenses, and the Path Towards Trustworthy AI. International Journal of Innovative Science and Research Technology, 1962. https://doi.org/10.38124/ijisrt/26jun1631
Vancouver
Pang J. Adversarial Machine Learning: Attacks, Defenses, and the Path Towards Trustworthy AI. International Journal of Innovative Science and Research Technology. 2026:1962. doi:10.38124/ijisrt/26jun1631
BibTeX
@article{Pang2026,
author = {Pang, Jieyao},
title = {Adversarial Machine Learning: Attacks, Defenses, and the Path Towards Trustworthy AI},
journal = {International Journal of Innovative Science and Research Technology},
year = {2026},
pages = {1962},
doi = {10.38124/ijisrt/26jun1631}
}
EUVIMED