fix: replace your-org placeholders, add paper link
Browse files
README.md
CHANGED
|
@@ -18,11 +18,11 @@ metrics:
|
|
| 18 |
- auroc
|
| 19 |
---
|
| 20 |
|
| 21 |
-
# GDNet
|
| 22 |
|
| 23 |
-
GDNet
|
| 24 |
|
| 25 |
-
This repository contains the weights and configuration. Code is at [github.com/lupingQAQ/gdnet](https://github.com/lupingQAQ/gdnet). The technical report is at [paper/GDNet
|
| 26 |
|
| 27 |
## Model details
|
| 28 |
|
|
@@ -107,7 +107,7 @@ The model outputs a probability and a distance, not a fact. Treat low-confidence
|
|
| 107 |
|
| 108 |
```bibtex
|
| 109 |
@software{gdnet2026,
|
| 110 |
-
title = {GDNet
|
| 111 |
year = {2026},
|
| 112 |
url = {https://github.com/lupingQAQ/gdnet},
|
| 113 |
note = {Model: https://huggingface.co/luping123/gdnet-v5}
|
|
|
|
| 18 |
- auroc
|
| 19 |
---
|
| 20 |
|
| 21 |
+
# GDNet
|
| 22 |
|
| 23 |
+
GDNet identifies security products and services from the first five packets of a network flow. It reports a product label, a type, a tier, and an open-set distance. Flows that do not match a known product are rejected as unknown.
|
| 24 |
|
| 25 |
+
This repository contains the weights and configuration. Code is at [github.com/lupingQAQ/gdnet](https://github.com/lupingQAQ/gdnet). The technical report is at [paper/GDNet.pdf](https://github.com/lupingQAQ/gdnet/blob/main/paper/GDNet.pdf).
|
| 26 |
|
| 27 |
## Model details
|
| 28 |
|
|
|
|
| 107 |
|
| 108 |
```bibtex
|
| 109 |
@software{gdnet2026,
|
| 110 |
+
title = {GDNet: Byte-level traffic classification for security product discovery},
|
| 111 |
year = {2026},
|
| 112 |
url = {https://github.com/lupingQAQ/gdnet},
|
| 113 |
note = {Model: https://huggingface.co/luping123/gdnet-v5}
|