58 lines
916 B
Markdown
58 lines
916 B
Markdown
|
---
|
||
|
|
library_name: transformers
|
||
|
|
pipeline_tag: text-generation
|
||
|
|
tags:
|
||
|
|
- llama
|
||
|
|
- text-generation
|
||
|
|
- cybersecurity
|
||
|
|
- intrusion-detection
|
||
|
|
- ai-ngfw
|
||
|
|
---
|
||
|
|
|
||
|
|
# llama-aingfw
|
||
|
|
|
||
|
|
Fine-tuned Llama model for network intrusion detection classification.
|
||
|
|
|
||
|
|
## Description
|
||
|
|
|
||
|
|
This model was fine-tuned for network intrusion detection tasks using structured network flow features.
|
||
|
|
|
||
|
|
The model classifies traffic into:
|
||
|
|
|
||
|
|
- normal
|
||
|
|
- dos
|
||
|
|
- bruteforce
|
||
|
|
- web_attack
|
||
|
|
- botnet
|
||
|
|
- reconnaissance
|
||
|
|
- other_attack
|
||
|
|
|
||
|
|
## Base Architecture
|
||
|
|
|
||
|
|
- LlamaForCausalLM
|
||
|
|
- Transformers
|
||
|
|
|
||
|
|
## Example Prompt
|
||
|
|
|
||
|
|
Network Intrusion Detection Task
|
||
|
|
|
||
|
|
Classify into:
|
||
|
|
normal, dos, bruteforce, web_attack, botnet, reconnaissance, other_attack
|
||
|
|
|
||
|
|
Features:
|
||
|
|
Port: 80
|
||
|
|
Duration: 1000
|
||
|
|
Fwd Packets: 10
|
||
|
|
Bwd Packets: 8
|
||
|
|
Bytes/s: 500
|
||
|
|
Packets/s: 20
|
||
|
|
SYN: 1
|
||
|
|
ACK: 1
|
||
|
|
RST: 0
|
||
|
|
|
||
|
|
Answer:
|
||
|
|
|
||
|
|
## Intended Use
|
||
|
|
|
||
|
|
Research, testing, and educational demonstrations of AI-assisted network intrusion detection systems.
|