A continuously updated collection of CodeLLM papers

Resources for our ICSE'24 poster: Prompt-Enhanced Software Vulnerability Detection Using ChatGPT.

A Novel Benchmark evaluating the Deep Capability of Vulnerability Detection with Large Language Models

SecLLMHolmes is a generalized, fully automated, and scalable framework to systematically evaluate the performance (i.e., accuracy and reasoning capabilities) of LLMs for vulnerability detection.

An overview of LLMs for cybersecurity.

MegaVul - The largest, high-quality, extensible, continuously updated, C/C++/Java vulnerability dataset

future-proof vulnerability detection benchmark, based on CVEs in open-source repos

An implementation of the ACL 2024 Findings paper "Generalization-Enhanced Code Vulnerability Detection via Multi-Task Instruction Fine-Tuning".

CodeBERT

This repository contains a PyTorch implementation of the ISSTA'24 paper "Graph Neural Networks for Vulnerability Detection: A Counterfactual Explanation".

The Learning Interpretability Tool: Interactively analyze ML models to understand their behavior in an extensible and framework agnostic interface.

Robust Collaborative Learning with Linear Gradient Overhead

[AISTATS 2024] BOBA: Byzantine-Robust Federated Learning with Label Skewness. Wenxuan Bao, Jun Wu, Jingrui He

Library for Byzantine attacks and aefences in federated learning.

Official Implementation of ICML'23 "Byzantine-Robust Learning on Heterogeneous Data via Gradient Splitting".

Statement-level deep learning model for automated software vulnerability detection in C/C++ (Accepted in MSR 2022)

A Transformer-based Line-Level Vulnerability Prediction

Finetuning large language models (LLMs) for vulnerability detection

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

Replication Package for "Compressing Pre-trained Models of Code into 3 MB", ASE 2022

The replication package of paper "Pre-training by Predicting Program Dependencies for Vulnerability Analysis Tasks"

CVEfixes: Automated Collection of Vulnerabilities and Their Fixes from Open-Source Software

[ICSE 2024 Industry Challenge Track] Official implementation of "ReposVul: A Repository-Level High-Quality Vulnerability Dataset".

This is the repository for the paper titled "Multitask-based Evaluation of Open-Source LLM on Software Vulnerability" accepted by TSE'24.

Repository for PrimeVul Vulnerability Detection Dataset