ICSE 2024
Fri 12 - Sun 21 April 2024 Lisbon, Portugal

Fuzz4All: Universal Fuzzing with Large Language Models


The purpose of this artifact is to provide a complete, reproducible, and easy-to-use environment for running Fuzz4All and reproducing the results in the paper.

As such, we aim for the following badges: 1. Available: We provide a publicly available artifact including both source code, scripts and raw data for Fuzz4All. 2. Reusable: We provide a complete docker image which includes full environment and detailed instructions to reproduce the main results in the paper.

Technology Skills and Systems

  1. OS: A Linux System with Docker Support;

  2. Hardware: GPU support. (this is optional but very highly recommended as without GPU support, the speed will be extremely slow)

  3. Familiarity with docker and running GPU related experiments