jinminhao/PANTS

[Usenix Security '25] Robustifying ML-powered Network Classifiers with PANTS

28
/ 100
Experimental

This project helps network operators test and strengthen their machine learning models used for network traffic classification. It takes your existing network traffic classifier and identifies subtle changes to network data that could trick it, then helps retrain the model to be more resilient. The end user is a network operator or security engineer responsible for maintaining robust and secure network operations.

No commits in the last 6 months.

Use this if you need to assess and improve the reliability of your ML-powered network traffic classifiers against sophisticated, targeted attacks that could disrupt services or compromise security.

Not ideal if you are looking for a general-purpose adversarial machine learning tool outside of network traffic classification or if you do not have strong CPU resources available for evaluation.

network-security traffic-classification network-operations intrusion-detection ML-security
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 12 / 25

How are scores calculated?

Stars

20

Forks

3

Language

Python

License

Last pushed

Aug 16, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/jinminhao/PANTS"

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