This repository contains the code and experiment data of the paper ELFuzz: Efficient Input Generation via LLM-driven Synthesis Over Fuzzer Space.

The experiment data is published on Figshare.

The code and environment to replicate the experiments are published as a Docker image. Run the following command to pull it:

docker pull ghcr.io/cychen2021/elfuzz:25.05.1

Instead, if you download the Docker image as a tarball from Figshare, you can import it using the following commands:

zstd -d "elfuzz_docker_<timetag>.tar.zst"
docker load --input "elfuzz_docker_<timetag>.tar"

After pulling/importing the image, run the following command to start the container:

docker run -it ghcr.io/cychen2021/elfuzz:25.05.1

This will enter a shell into the container. Then, following the instructions in /elfuzz/README.md (which is a symlink to docker_readme.md in this repository) to replicate the experiments.

The Docker image has only been tested on X86-64 machines.

Before building the Docker image, you should cd to the root of the ELFuzz source code and put elfuzz_baselines.tar.zst into tmp/.

The Docker image is built by the following command:

docker build --build-arg -t ghcr.io/cychen2021/elfuzz:25.05.1 -f .devcontainer/Dockerfile --target publish .

I tried my best to preserve the environment in the Docker image, keeping the replication package usable for as long as possible. However, there may be some aspects that I have not considered. If you encounter any issues that prevent you from using the package, please open an issue or launch a pull request.