EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Cognitive Network Intrusion Detection Systems: Anomaly and Malware Detection for Zero-Day Attack Resilience

Jimmy Agung Gunawan, Moses Laksono Singgih, Raden Venantius Hari Ginardi

Network · 18.06.2026 · 6 (2) · 41

DOI: 10.3390/network6020041 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Network, online erschienen am 18.06.2026. Verfasst von Jimmy Agung Gunawan und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 80 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Traditional Network Intrusion Detection Systems (NIDSs) face persistent challenges in detecting zero-day attacks due to concept drift, high false-positive rates, and limited adaptability. This research introduces a Cognitive Network Intrusion Detection System (CNIDS) whose central novelty is that effective zero-day handling does not arise from any single mechanism but from the interaction between continual representation learning, persistent vector memory, and human-aligned feedback. By reframing zero-day resilience as a continuous learning process rather than a static detection task, CNIDS emphasizes adaptive operational behavior over raw automated accuracy. The proposed framework integrates Continual Pre-Training (CPT) to align representations with evolving traffic, Supervised Fine-Tuning (SFT) to preserve precision on known attacks, and a Human-in-the-Loop Reinforcement Signal (HRS) that converts low-confidence alerts into structured learning updates. These components are unified through a vector database that functions as long-term episodic memory, enabling similarity-based reasoning and cross-dataset generalization. Ablation results show that disabling any component degrades zero-day adaptation: removing CPT increases drift sensitivity, removing vector memory prevents knowledge retention, and removing human feedback collapses learning to static inference. Using a class-exclusion zero-day protocol on NSL-KDD, UNSW-NB15, and CICIDS2017, CNIDS raises zero-day detection from 0% to 18.2% while maintaining precision above 80% and stabilizing false positives.

Zitieren

APA

Gunawan, J. A., Singgih, M. L., & Ginardi, R. V. H. (2026). Cognitive Network Intrusion Detection Systems: Anomaly and Malware Detection for Zero-Day Attack Resilience. Network, 6(2), 41. https://doi.org/10.3390/network6020041

Vancouver

Gunawan JA, Singgih ML, Ginardi RVH. Cognitive Network Intrusion Detection Systems: Anomaly and Malware Detection for Zero-Day Attack Resilience. Network. 2026;6(2):41. doi:10.3390/network6020041

BibTeX
@article{Gunawan2026,
  author = {Gunawan, Jimmy Agung and Singgih, Moses Laksono and Ginardi, Raden Venantius Hari},
  title = {Cognitive Network Intrusion Detection Systems: Anomaly and Malware Detection for Zero-Day Attack Resilience},
  journal = {Network},
  year = {2026},
  volume = {6},
  number = {2},
  pages = {41},
  doi = {10.3390/network6020041}
}
Kostenlos starten →