Network Traffic for Intrusion Detection with Attack and Normal Labels

A dataset of network traffic flows containing both normal and attack traffic for Intrusion Detection System (IDS) research. The dataset was sourced from Kaggle, but its author, collection time range, and specific size are not documented. It is intended for machine learning applications in cybersecurity.

Use Cases

• Train supervised classification models to distinguish attack from normal traffic based on labeled network flows.
• Benchmark feature engineering and AutoML pipelines for cyber security applications.
• Develop and evaluate time-series or LSTM-based models for detecting sequential attack patterns in network traffic.

Strengths

• Contains labeled data for both attack and normal traffic, enabling supervised learning.
• Platform tags indicate the dataset is intended for advanced modeling techniques like Gradient Boosting and LSTM.

Limitations

• Row count and file size are unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Last update date is unknown; freshness unverified.

Provenance

Source

Kaggle