There is a newer version of the record available.

Published April 11, 2024 | Version v1
Dataset Restricted

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)

  • 1. ROR icon University of Trento
  • 2. ROR icon Vrije Universiteit Amsterdam

Description

The Replication Package of

"Time-based Analysis on Software Vulnerability ML Detection: A Differentiated Replication"

Part 2 (Linux Dataset)

 
The zipped package includes:
  1. Datasets that we created using our methodology and the original dataset (from [NVD Vuldeepecker](https://github.com/CGCL-codes/VulDeePecker))
    - retrospective test
    - believed_perspective test
    - perspective test
  2. Pre-trained models that we generated during our evaluation (3 test results for each time point in the timeline [2011-2017]).
We also added the summarized result files (.xlsx)
1. Timeline of Datasets.xlsx
2. ML Evaluations.xlsx
and the notebook to produce the charts in the paper: Charts.ipynb
 
Please refer to 
https://zenodo.org/records/10965516 for Part 1 NVD Vuldeepecker Dataset

Files

Restricted

The record is publicly accessible, but files are restricted. <a href="https://zenodo.org/account/settings/login?next=https://zenodo.org/records/10960663">Log in</a> to check if you have access.

Additional details

Funding

European Commission
Sec4AI4Sec - Cybersecurity for AI-Augmented Systems 101120393
European Commission
AssureMOSS - Assurance and certification in secure Multi-party Open Software and Services. 952647
Dutch Research Council
Theseus NWA.1215.18.006
Dutch Research Council
HEWSTI KIC1.VE01.20.004