1,000,000,000 network event records categorized into normal traffic and three specific attack types: DDoS, SQL injection (SQLi), and BruteForce. The dataset includes a pre-trained CatBoost model achieving 99.9% detection accuracy across these security event classes.
Use Cases
- Train high-scale intrusion detection systems to identify DDoS patterns within massive network logs
- Evaluate the performance of the included CatBoost model against SQLi and BruteForce event labels
- Benchmark big data processing frameworks using the 1 billion row event volume
- Develop anomaly detection algorithms specifically targeting SQL injection signatures in network traffic
Strengths
- Contains over 1,000,000,000 individual network event rows
- Includes labeled data for DDoS, SQLi, and BruteForce attack vectors
- Accompanied by a pre-trained CatBoost classification model
- Demonstrates a 99.9% accuracy rate on the provided network traffic samples