HackerSignal: A Multi-Source, CVE-Linked Corpus and Prospective Benchmark for Cyber Threat Intelligence

Benjamin M. Ampel, Sagar Samtani
Last updated on Nov 5, 2026
PDF Code DOI
In Plain Terms

This paper introduces HackerSignal, a very large public dataset that stitches together 7.45 million documents from hacker forums, exploit databases, vulnerability advisories, and software fix commits collected over 36 years. Everything is connected through shared CVE vulnerability identifiers, letting researchers trace a security flaw from early hacker chatter all the way to its official patch. The authors demonstrate three AI benchmark tasks the dataset enables and release diagnostics and documentation to support responsible reuse. Accepted as a poster at the NeurIPS 2026 Evaluations & Datasets Track.

Artifacts

PDF Code DOI

Related Papers

Cite this

APA Ampel, B. M., & Samtani, S. (2026). HackerSignal: A Multi-Source, CVE-Linked Corpus and Prospective Benchmark for Cyber Threat Intelligence. In Proceedings of the Fortieth Annual Conference on Neural Information Processing Systems (NeurIPS 2026), Evaluations & Datasets Track. https://doi.org/10.48550/arXiv.2605.03158
BibTeX
@inproceedings{ampel2026hackersignal,
  title={HackerSignal: A Multi-Source, CVE-Linked Corpus and Prospective Benchmark for Cyber Threat Intelligence},
  author={Benjamin M. Ampel and Sagar Samtani},
  booktitle={Proceedings of the Fortieth Annual Conference on Neural Information Processing Systems (NeurIPS 2026), Evaluations & Datasets Track},
  year={2026},
  doi={10.48550/arXiv.2605.03158}
}
Cyber Threat Intelligence Datasets and Benchmarks Vulnerability Management
Benjamin M. Ampel

Benjamin M. Ampel

Assistant Professor in Computer Information Systems and Director, Center for CyberAI Research (CCAIR)

My research focuses on AI-enabled Cybersecurity, including Cyber Threat Intelligence, Large Language Models, and Phishing Detection.