Systemic Adversarial Vulnerability in Deep Learning Classifiers: A Cross-Model Experimental Analysis
INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT · 27.04.2026 · 10 (04) · 1-9
DOI: 10.55041/ijsrem61314 ↗Kurz gefasst
Fachartikel in der Zeitschrift INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT, online erschienen am 27.04.2026. Verfasst von Rahul J. Teradal und 1 weiteren Autor:innen.
Abstract (Originalsprache)
Abstract—Adversarial attacks demonstrate the existence of severe weaknesses in deep learning image classifiers due to misclassification, caused by a small, precisely-designed input per- turbation. This work aims to experimentally test the adversarial robustness and the extent to which adversarial vulnerability can be model-dependent or systemic. There are two controlled experiments. First, on a pretrained ResNet-18 model, Fast Gra- dient Sign Method (FGSM), Projected Gradient Descent (PGD) and Carlini-Wagner (CW) attacks are applied to discuss the impact of attack sophistication. Second, cross-model robustness is compared by means of eight pretrained image classification models to evaluate FGSM for cross-model robustness. The findings indicate that optimization-based attacks are much better than single-step attacks and more complex architectures are more robust and lightweight models are more sensitive. These results suggest that adversarial vulnerability is architecture-dependent and exists irrespective of a model. The paper also discusses defense and recovery processes and points out how the principles of Responsible AI can be used to construct high-quality and trustworthy adversarial defenses. Index Terms—Adversarial Attacks; Deep Learning; Image Classification; Model Robustness; Responsible AI
Zitieren
APA
Teradal, R. J., & Nabiwale, M. M. (2026). Systemic Adversarial Vulnerability in Deep Learning Classifiers: A Cross-Model Experimental Analysis. INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT, 10(04), 1-9. https://doi.org/10.55041/ijsrem61314
Vancouver
Teradal RJ, Nabiwale MM. Systemic Adversarial Vulnerability in Deep Learning Classifiers: A Cross-Model Experimental Analysis. INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT. 2026;10(04):1-9. doi:10.55041/ijsrem61314
BibTeX
@article{Teradal2026,
author = {Teradal, Rahul J. and Nabiwale, Misbah Mansoor},
title = {Systemic Adversarial Vulnerability in Deep Learning Classifiers: A Cross-Model Experimental Analysis},
journal = {INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT},
year = {2026},
volume = {10},
number = {04},
pages = {1--9},
doi = {10.55041/ijsrem61314}
}
EUVIMED