EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Uncertainty-Aware Evidential Adversarial Defense for Cloud Intrusion Detection under GAN-Based Evasion Attacks

Jiawen Luo, Samuel Price

International Journal of Advanced Engineering and Technology Research · 20.07.2026 · 2 (3) · 42-48

DOI: 10.54097/6bm9sm08 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Advanced Engineering and Technology Research, online erschienen am 20.07.2026. Verfasst von Jiawen Luo und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cloud intrusion detection systems (IDSs) increasingly depend on deep neural classifiers, which are vulnerable to adversarial evasion attacks—including realistic, GAN-crafted traffic—that flip malicious flows to benign with near-imperceptible, functionally consistent perturbations. Adversarial training (AT) hardens the decision boundary but yields overconfident point predictions: a hardened detector still cannot signal when an input is suspicious, and Bayesian or ensemble uncertainty estimators that could do so require many forward passes, which is impractical at cloud line rate. We propose UA-EAD, an uncertainty-aware evidential adversarial defense that (i) equips the detector with an evidential (Dirichlet) head yielding calibrated predictive uncertainty in a single forward pass, (ii) trains it with an uncertainty-weighted adversarial objective plus a consistency regularizer that concentrates robustness on the most uncertain, near-boundary flows, and (iii) uses the resulting uncertainty for selective prediction, abstaining on inputs it cannot confidently classify. On NSL-KDD under FGSM, BIM, PGD, C&W, and a black-box WGAN-GP transfer attack, UA-EAD matches the strongest AT baselines in robust accuracy (97.4%) while attaining the highest clean accuracy (98.1%). Its single-pass evidential uncertainty equals maximum-softmax-probability and surpasses Monte-Carlo Dropout for adversarial detection at 21x lower inference cost, and yields the best adversarial-detection AUROC among robust models. Selective prediction lifts accuracy on 17 novel (out-of-distribution) attack types from 76.9% to 87.0% at 70% coverage. We further report an empirical robustness–detectability trade-off that clarifies why hardening alone is insufficient for trustworthy cloud IDS.

Zitieren

APA

Luo, J., & Price, S. (2026). Uncertainty-Aware Evidential Adversarial Defense for Cloud Intrusion Detection under GAN-Based Evasion Attacks. International Journal of Advanced Engineering and Technology Research, 2(3), 42-48. https://doi.org/10.54097/6bm9sm08

Vancouver

Luo J, Price S. Uncertainty-Aware Evidential Adversarial Defense for Cloud Intrusion Detection under GAN-Based Evasion Attacks. International Journal of Advanced Engineering and Technology Research. 2026;2(3):42-48. doi:10.54097/6bm9sm08

BibTeX
@article{Luo2026,
  author = {Luo, Jiawen and Price, Samuel},
  title = {Uncertainty-Aware Evidential Adversarial Defense for Cloud Intrusion Detection under GAN-Based Evasion Attacks},
  journal = {International Journal of Advanced Engineering and Technology Research},
  year = {2026},
  volume = {2},
  number = {3},
  pages = {42--48},
  doi = {10.54097/6bm9sm08}
}
Kostenlos starten →