Botnet SDN ML: Botnet Detection Data for Software-Defined Networks

Source materials for botnet detection experiments specifically within Software-Defined Networking (SDN) environments using neural networks. Created by GitHub user gdellapenna and last updated in June 2018, it targets the identification of malicious traffic patterns in programmable network architectures.

Use Cases

• Training neural networks to classify SDN traffic flows as benign or botnet-infected
• Evaluating the performance of machine learning models on software-defined network topologies
• Benchmarking anomaly detection algorithms against 2018-era botnet signatures

Strengths

• Focuses specifically on Software-Defined Networking (SDN) architectures rather than traditional hardware-based networks
• Includes source materials specifically formatted for neural network experimentation
• Provides a historical snapshot of botnet traffic patterns from the 2018 period

Limitations

• Lack of documentation regarding feature definitions or data schema
• Temporal staleness may limit effectiveness against modern 2024 botnet evolution
• No explicit license or usage restrictions provided by the author

Provenance

Source

gdellapenna (GitHub)

Time Range

Updated 2018

Freshness

The dataset is static and has not been updated since June 2018.