AttackQA: Development and Adoption of a Dataset for Assisting Cybersecurity Operations using Fine-tuned and Open-Source LLMs

ICLR 2025 Conference Submission2243 Authors

Keywords: LLM, Large Language Models, Generative AI, Dataset, Cyber, Security, MITRE, Chatbot, Judging, Quality, Control, Open source, RAG, Retrieval, Augmented, Generation

TL;DR: A new dataset to train or tune models to gain cybersecurity expertise, along with an evaluation of fine-tuned open-source models that outperform proprietary LLMs that are over 100x as large on the dataset

Abstract: Retrieval-augmented generation (RAG) on specialized domain datasets has shown improved performance when large language models (LLMs) are fine-tuned for generating responses to user queries. In this study, we develop a cybersecurity question-answering (Q\&A) dataset, called AttackQA, and employ it to build a RAG-based Q\&A system designed for analysts in security operations centers. The dataset comprises 25,335 Q\&A pairs, accompanied by rationales to facilitate fine-tuning and evaluation. 80\% of the dataset was generated with help of a lightweight open-source LLM (LLama 3 8B), which produced over 1100 tokens per second with full 16-bit precision on specialized hardware. To ensure dataset quality, we fine-tuned LLama 3 70B to detect and reject low-quality Q\&A pairs. In using the dataset for RAG, we demonstrate that fine-tuning open-source embeddings and LLMs can yield superior accuracy compared to OpenAI's state-of-the-art proprietary embedding and LLM (GPT-4o). Furthermore, we use Llama 3.1 405B as a judge to evaluate answer correctness, enabling the creation of a fully open-source, high-speed RAG and evaluation pipeline with an associated benchmark.

Primary Area: datasets and benchmarks

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 2243