netFound-640M-base
Attention: this model was designed for netFound-v1 and currently replaced by a family of new netFound-v2 models. Please, see the github repo for links and instructions, and https://huggingface.co/snlucsb/models for netFound-v2 models.
Description
netFound is a network traffic foundation model that uses transformer architecture and includes a pretraining phase on unlabeled data to achieve high results.
Key features:
- netFound takes raw PCAP data as input
- netFound can (and need) be pretrained on the unlabeled dataset
- netFound uses Hierarchical Transformer architecture to take into account packet burst and flow behavior
- netFound uses burst metadata (inter arrival time, number of bytes per burst, etc)
Source code
Pretraining dataset
For pretraining, we used a private real-world dataset consisting of more than 450mln network flows. The model was pretrained for approximately 1 epoch (iterated through ~480mln flows).
Checkpoint
Model: Large (16 heads, 24 hidden layers, 1024 hidden size)
Total params: 643,825,672
January 17, 2025
Paper
