EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

EdgeGuard: Source-aware robustness and edge-feasibility evaluation of lightweight email phishing detectors under cross-LLM generated attacks

Momina Bibi, Kamran Ahmad Awan, Ling-Chun Liu, Chin-Ling Chen, Faris Alanazi, Meshari Huwaytim Alanazi, Mueen Uddin

Journal of King Saud University Computer and Information Sciences · 2026-11 · 38 (9)

DOI: 10.1007/s44443-026-01351-9 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of King Saud University Computer and Information Sciences, online erschienen am 02.11.2026. Verfasst von Momina Bibi und 6 weiteren Autor:innen. Die Arbeit nennt 64 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science and Technology Council, Deanship of Scientific Research at Northern Border University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Email phishing detection is increasingly affected by source shift because generated or rewritten phishing emails may differ from the human-authored samples used to train conventional detectors. This study presents EdgeGuard as a controlled source-aware evaluation protocol for testing lightweight phishing detectors under human-authored and LLM-generated phishing conditions while considering CPU-only edge feasibility. Emails are represented using sparse TF–IDF features with 50,000 unigram–bigram terms and document-frequency filtering. Logistic Regression and Linear SVM are trained on human-authored Enron–TREC email data and evaluated on balanced human, GPT-3.5, Llama-3.2, and Gemma 2 phishing conditions using accuracy, precision, recall, F1-score, false-positive rate, false-negative rate, Attack Success Rate (ASR), and RDG as a supporting accuracy-difference summary. Results show that generated phishing does not uniformly reduce detectability. GPT-3.5 samples achieved 99.80% recall because the prompt design preserved and amplified conventional phishing cues such as urgency, account verification, security warnings, and fake-link instructions. In contrast, Llama-3.2 and Gemma 2 produced larger source-shift effects in the evaluated setting, reducing recall and increasing false negatives for both lightweight detectors. The detectors remained computationally efficient under CPU-only inference, with mean single-email latencies of 0.18 ms for Logistic Regression and 0.08 ms for Linear SVM. Feature-compression analysis further showed that reducing the TF–IDF vocabulary from 50,000 to 5000 features substantially decreased serialized classifier size from 0.38 MB to 0.04 MB while preserving high accuracy, although latency remained implementation-dependent under CPU-only execution. These findings show that lightweight TF–IDF detectors can be edge-feasible, but their robustness must be evaluated separately across generated phishing sources rather than inferred from static human-authored benchmarks alone.

Förderung

  • National Science and Technology Council
  • Deanship of Scientific Research at Northern Border University

Zitieren

APA

Bibi, M., Awan, K. A., Liu, L., Chen, C., Alanazi, F., Alanazi, M. H., & Uddin, M. (2026). EdgeGuard: Source-aware robustness and edge-feasibility evaluation of lightweight email phishing detectors under cross-LLM generated attacks. Journal of King Saud University Computer and Information Sciences, 38(9). https://doi.org/10.1007/s44443-026-01351-9

Vancouver

Bibi M, Awan KA, Liu L, Chen C, Alanazi F, Alanazi MH, et al. EdgeGuard: Source-aware robustness and edge-feasibility evaluation of lightweight email phishing detectors under cross-LLM generated attacks. Journal of King Saud University Computer and Information Sciences. 2026;38(9). doi:10.1007/s44443-026-01351-9

BibTeX
@article{Bibi2026,
  author = {Bibi, Momina and Awan, Kamran Ahmad and Liu, Ling-Chun and Chen, Chin-Ling and Alanazi, Faris and Alanazi, Meshari Huwaytim and Uddin, Mueen},
  title = {EdgeGuard: Source-aware robustness and edge-feasibility evaluation of lightweight email phishing detectors under cross-LLM generated attacks},
  journal = {Journal of King Saud University Computer and Information Sciences},
  year = {2026},
  volume = {38},
  number = {9},
  doi = {10.1007/s44443-026-01351-9}
}
Kostenlos starten →