Skip to content

Latest commit

 

History

History
50 lines (34 loc) · 2.59 KB

README.md

File metadata and controls

50 lines (34 loc) · 2.59 KB
Raw

UNAVOIDS: Unsupervised and Nonparametric Approach for Visualizing Outliers and Invariant Detection Scoring

Code Summary

aggregate.py: this script aggregates the scores outputted by expriments.py

experiments.py: This script runs UNAVIODS and some comparison algorithms across a grid of parameters on a window specified by a command line argument.

genPrevelanceArrs.py: Thus script creates Pis_\[i\].npy for each i, where i corresponds to the index of the i^th prevelance in the array Pis each Pis_\[i\].npy contains a n' < n length vector of indicies, such that the prevelance of outliers in the subset pointed to by these indicies corresponds to the ith value of Pis.

genSimulatedDataSet.py: This script generates a simulated dataset

genSimulationNCDFs.py: This script finds the NCDFs for simulated data using different norms and numbers of features, then creates CSV files for LaTeX to plot the NCDFs

loadAndCleanDoH.py: This file loads and cleans the data from the CIRA-CIC-DoHBrw-2020 data set

loadAndCleanIDS.py: This file loads and cleans the data from the CICIDS2017 data set

txtToLatex.py: This file loads the TXT file outputted by aggregate.py and creates several CSV's saved in \[outfolder\]. These can be used by our LaTeX code to create latex plots.

txtToLatex.py: the unavoids outlier detection and visualization library. All functions have a docstring describe their use.

main.py: basic usuage example of the unavioids library

Patent

W. A. Yousef, I. Traore, and W. Briguglio: "Unsupervised and nonparametric approach for visualizing outliers and invariant detection scoring", US Patent 63168686 (pending).

References

W. A. Yousef, I. Traoré and W. Briguglio, "UN-AVOIDS: Unsupervised and Nonparametric Approach for Visualizing Outliers and Invariant Detection Scoring," in IEEE Transactions on Information Forensics and Security, vol. 16, pp. 5195-5210, 2021, doi: 10.1109/TIFS.2021.3125608.

This repo as a capsul on CodeOcean

https://codeocean.com/capsule/2122579/tree/v1

The repo as a PyPi package

https://pypi.org/project/unavoids/

Citation

Please, cite this work as:

@ARTICLE{Yousef2021UNAVOIDS,
  author={Yousef, Waleed A. and Traoré, Issa and Briguglio, William},
  journal={IEEE Transactions on Information Forensics and Security}, 
  title={UN-AVOIDS: Unsupervised and Nonparametric Approach for Visualizing Outliers and Invariant Detection Scoring}, 
  year={2021},
  volume={16},
  pages={5195-5210},
  doi={10.1109/TIFS.2021.3125608}}