Estimating adversarial transferability from feature-importance similarity in explainable intrusion detection systems

Creative Commons License

Abdlatef A., Abdulkareem M., Cakir D.

International Journal of Information Security, cilt.25, sa.5, 2026 (SCI-Expanded, Scopus)

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 25 Sayı: 5
  • Basım Tarihi: 2026
  • Doi Numarası: 10.1007/s10207-026-01333-y
  • Dergi Adı: International Journal of Information Security
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, ABI/INFORM, Aerospace Database, Applied Science & Technology Source, Compendex, Criminal Justice Abstracts, INSPEC, Criminal Justice Periodical Index, Academic Search Ultimate (EBSCO), Social Science Premium Collection (ProQuest), Business Source Ultimate (EBSCO), Criminology Collection (ProQuest), Engineering Source (EBSCO), Pharma Collection (ProQuest), Technology Collection (ProQuest)
  • Anahtar Kelimeler: Adversarial attacks, Adversarial transferability, Explainable AI (XAI), Feature importance, Intrusion detection systems (IDS)
  • Açık Arşiv Koleksiyonu: AVESİS Açık Erişim Koleksiyonu
  • Galatasaray Üniversitesi Adresli: Hayır

Özet

Machine Learning (ML)-based Intrusion Detection Systems (IDS) are critical for defending against cyber threats but remain vulnerable to adversarial attacks, posing risks to system reliability and security. This study investigates the transferability of adversarial attacks across XGBoost and LightGBM models in IDS and uses Explainable AI (XAI) techniques to identify features that influence model decisions. Experiments on the CICIDS-2017 and NSL-KDD datasets demonstrate cross-model adversarial transferability, with accuracy reductions of 8.75% and 10.59% for XGBoost and LightGBM, respectively. The XAI-informed analysis further shows that feature-importance patterns can be used to examine model vulnerability under adversarial perturbations. Under direct adversarial testing, XGBoost exhibited a 6.18% reduction in accuracy, illustrating the vulnerability associated with perturbations targeting highly ranked features. Building on prior research linking feature importance to adversarial transferability, this study operationalizes that relationship in the IDS domain through a heuristic formulation based on correlations between model-specific feature-importance vectors. The proposed formulation is intended as a practical approximation for assessing cross-model vulnerability rather than as a deterministic predictor.