Comparison of Adversarially Robust NIDS Models (2023–2025)

Sudip Saha published a dataset comparing recent state-of-the-art adversarially robust Network Intrusion Detection System (NIDS) models. The dataset is a 5.5 KB Excel file, last updated on June 1, 2026. It is shared under a CC-BY-4.0 license on the figshare platform.

Use Cases

• Benchmarking new NIDS models against recent state-of-the-art methods based on the described comparison.
• Analyzing trends in adversarial robustness for network security based on the 2023–2025 model survey.
• Informing the design of robust ML models for cybersecurity based on the comparative evaluation.

Strengths

• Dataset is small (5.5 KB), facilitating quick download and inspection.
• Focuses on a specific, timely research area (adversarially robust NIDS models from 2023–2025).
• Has a clear, permissive license (CC-BY-4.0).

Limitations

• The dataset's row count and specific column structure are unknown, limiting suitability assessment.
• Description metadata is limited; actual data quality and comparison methodology require manual inspection after download.
• The small file size suggests the dataset likely contains summary or metadata, not raw network traffic data.

Provenance

Source

figshare

Time Range

Covers models from 2023 to 2025.

Freshness

Last updated 2026-06-01 17:55:09