Today's cat is tomorrow's dog: accounting for time-based changes in the labels of ML vulnerability detection approaches (Replication Package Part 2: Linux dataset)

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 2 (LINUX Dataset)

This repository includes:

Code that contains the codes to replicate some parts of this study:a. 1_generate_datasets implements our methodology to generate the datasets.b. 2_run_models runs the ML models during the evaluation.c. 3_result_replication generates charts presented in the paper from the ML evaluation results.

Datasets that contain 2 folders:a. original datasets: 1 from NVD Vuldeepecker and 3 extracted from BigVul.

b. LINUX datasets: train, validation, test sets for each time of observation extracted using our methodology from BigVul dataset for project linux.

Pretrained-models that we generated during our evaluation (3 test results for each time point in the timeline [2011-2019]).

Results of our evaluation, the folder ALL contains the overall results and other folders are results by model.

Please refer to the following repositories for the other datasets and pre-trained models:

- Part 1 NVD Vuldeeepecker : https://doi.org/10.5281/zenodo.8207883

- Part 3 OPENSSL : https://doi.org/10.5281/zenodo.10966117

- Part 4 POPPLER : https://doi.org/10.5281/zenodo.14713143