Published September 11, 2024
| Version v5
Conference paper
Restricted
Today's cat is tomorrow's dog: accounting for time-based changes in the labels of ML vulnerability detection approaches (Replication Package Part 1: NVD Vuldeepecker Dataset)
Creators
Description
The Replication Package of
"Today's cat is tomorrow's dog: accounting for time-based changes in the labels of ML vulnerability detection approaches"
Part 1 (NVD Vuldeepecker Dataset)
NOTE
The files below are marked restricted, in the sense that they are not publicly downloadable.
However, as a reviewer, through the link we shared with you, you can download the files by clicking the download button.
The rest of the datasets (because of Zenodo size limit) would be available upon acceptance.
However, as a reviewer, through the link we shared with you, you can download the files by clicking the download button.
The rest of the datasets (because of Zenodo size limit) would be available upon acceptance.
The zipped package (time_based_analysis.zip) includes:
- Code that implements our methodology to generate the datasets and to run the ML models during evaluation
- Datasets that we created using our methodology and the original dataset (from NVD Vuldeepecker)
- on_paper test = retrospective test
- field test = perspective test
- addNs test = believed_perspective test (additional extension) - Pre-trained models that we generated during our evaluation (3 test results for each time point in the timeline [2008-2017]).
- Results of our evaluation.
We also added the summarized result files (.xlsx)
1. Timeline of Datasets.xlsx
2. MLEvaluation_Result.xlsx
and the notebook to produce the charts in the paper: Charts.ipynb.