VulScribeR

Official repository for our paper:

VulScribeR: Exploring RAG-based Vulnerability Augmentation with LLMs

Datasets

Primary Datasets

Bigvul_train, Bigvul test, Bigvul_val

Reveal, Devign

VGX and Vulgen (used as baselines)

VGX Full dataset, Vulgen Full dataset from VGX paper

Retriever's output

All pair matchings, including for mutation and random ones for RQ2

Our Generated Vulnerable Samples

Filtered Datasets for All RQs, Unfiltered Datasets for All RQs
The unfiltered dataset contains samples from the Generator and hasn't gone through the Verification phase. They also include extra metadata that shows which clean_vul pair was used for generation, plus the vul lines.

How to use?

See here

How to train DLVD models

Go to the models directory, the readme for each model explains how to use each of the models