Journal: Scientific Reports

Article Title: Conformable Fractional Deep Neural Networks (CFDNN) for high-speed cyber-attack detection

doi: 10.1038/s41598-026-45213-w

Figure Lengend Snippet: Fractional order ( \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\alpha$$\end{document} ) impact analysis on CFDNN performance for (a) NSL-KDD and (b) CIC-IDS2018 datasets. The highlighted region ( \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$1.2 \le \alpha \le 1.8$$\end{document} ) represents the optimal performance range.

Article Snippet: The raw data utilized in this study are derived from the publicly available NSL-KDD and CIC-IDS2018 datasets, both accessible through the University of New Brunswick (UNB) repository.

Techniques:

Journal: Scientific Reports

Article Title: Conformable Fractional Deep Neural Networks (CFDNN) for high-speed cyber-attack detection

doi: 10.1038/s41598-026-45213-w

Figure Lengend Snippet: Multi-dimensional performance analysis: (a) NSL-KDD performance radar, (b) CIC-IDS2018 performance radar, (c) Optimal performance comparison at \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\alpha =1.8$$\end{document} , (d) Normalized computational time analysis.

Article Snippet: The raw data utilized in this study are derived from the publicly available NSL-KDD and CIC-IDS2018 datasets, both accessible through the University of New Brunswick (UNB) repository.

Techniques: Comparison