@inproceedings{paper-nyu-ctf-bench,
  title = {{NYU CTF Bench: A Scalable Open-Source Benchmark Dataset for Evaluating LLMs in Offensive Security}},
  author = {{Minghao Shao} and {Sofija Jancheska} and {Meet Udeshi} and {Brendan Dolan-Gavitt} and {Haoran Xi} and {Kimberly Milner} and {Boyuan Chen} and {Max Yin} and {Siddharth Garg} and {Prashanth Krishnamurthy} and {Farshad Khorrami} and {Ramesh Karri} and {Muhammad Shafique}},
  year = {2024},
  url = {https://proceedings.neurips.cc/paper_files/paper/2024/hash/69d97a6493fbf016fff0a751f253ad18-Abstract-Datasets_and_Benchmarks_Track.html},
  booktitle = {NeurIPS 2024 Datasets and Benchmarks},
  doi = {10.52202/079017-1832},
  eprint = {2406.05590},
  archivePrefix = {arXiv}
}