pVoxel

Point cloud analysis based false postive (FP) identification for machine learning based malicious traffic detection systems.

Point Cloud Analysis for ML-Based Malicious Traffic Detection: Reducing Majorities of False Positive Alarms
In Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications Security (CCS'23).
Chuanpu Fu, Qi Li, Ke Xu and Jianping Wu.

This repository provides a simplified demo for the paper, which is easy to reproduce.

Please find proofs in the full version paper.

0x00 Environment

AWS EC2 c4.4xlarge, 100GB SSD, canonical Ubuntu 22.04 LTS (amd64, 3/3/2023).

0x01 Software

start.sh is an all-in-one script to build and run this demo:

git clone https://github.com/fuchuanpu/pVoxel.git
cd pVoxel
chmod +x start.sh && ./start.sh

0x02 Reference

@inproceedings{CCS23-pVoxel,
  author    = {Chuanpu Fu and
               others},
  title     = {Point Cloud Analysis for ML-Based Malicious Traffic Detection: Reducing Majorities of False Positive Alarms},
  booktitle = {CCS},
  publisher = {ACM},
  year      = {2023}
}

0x03 Maintainer

Chuanpu Fu