ole-knf/A-bidirectional-GPT-approach-for-detecting-malicious-network-traffic

This approach of Intrusion Detection uses two GPT models, which are trained on normal network traffic, to predict sequences of communication patterns and thereby score network packets.

27
/ 100
Experimental

This project helps network security analysts detect unusual or malicious activity by analyzing network traffic. It takes raw network packet capture files (PCAP) as input and uses two AI models to score each packet's likelihood of being normal. The output includes real-time alerts for suspicious packets and a detailed plot showing scores over time, highlighting potential attacks. Network security specialists, incident responders, or operations engineers responsible for monitoring industrial control systems would use this tool.

No commits in the last 6 months.

Use this if you need to identify subtle anomalies in network communication patterns that might indicate a cyber-physical attack, especially within critical infrastructure like water distribution systems.

Not ideal if you need a pre-trained, ready-to-deploy intrusion detection system for general enterprise IT networks, as this project requires training with specific normal traffic data.

network-security intrusion-detection cyber-physical-systems industrial-control-systems network-monitoring
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 14 / 25

How are scores calculated?

Stars

11

Forks

3

Language

Python

License

Last pushed

Oct 03, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/ole-knf/A-bidirectional-GPT-approach-for-detecting-malicious-network-traffic"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.