Here are two recent publications on AI topics in artificial intelligence that I collaborated on. The first paper is a preprint under submission and discusses techniques to train a custom reasoning model for security operations center triage tasks:

Amol Khanna, Manu Nandan, Cristian Viorel Popa, Joan Pujol-Roig, Diana Bolocan, Laura Vasilie, Alexandru Apostu, Chase Helwig, Mihaela Gaman, Michael Brautbar, Edward Raff, Chase Midler, and Sven Krasser, “Cybersecurity Detection Classification with Reasoning-enabled Language Models.” 2026. Available at: https://arxiv.org/abs/2607.28460 
@misc{khanna2026cybersecuritydetectionclassificationreasoningenabled,
  title = {Cybersecurity Detection Classification with Reasoning-enabled Language Models},
  author = {Khanna, Amol and Nandan, Manu and Popa, Cristian Viorel and Pujol-Roig, Joan and Bolocan, Diana and Vasilie, Laura and Apostu, Alexandru and Helwig, Chase and Gaman, Mihaela and Brautbar, Michael and Raff, Edward and Midler, Chase and Krasser, Sven},
  year = {2026},
  eprint = {2607.28460},
  archiveprefix = {arXiv},
  primaryclass = {cs.LG},
  url = {https://arxiv.org/abs/2607.28460}
}

The second paper is a position paper on challenges applying AI on cybersecurity topics. You can find the preprint below. The final paper was presented at the Workshop on Rethinking Malware Analysis (WoRMA) 2026:

Edward Raff, Maor Ashkenazi, Sagar Samtani, David J. Elkind, and Sven Krasser, “Cybersecurity is the True Frontier for Generative AI Success or Failure.” 2026. Available at: https://arxiv.org/abs/2606.28929 
@misc{raff2026cybersecuritytruefrontiergenerative,
  title = {Cybersecurity is the True Frontier for Generative AI Success or Failure},
  author = {Raff, Edward and Ashkenazi, Maor and Samtani, Sagar and Elkind, David J. and Krasser, Sven},
  year = {2026},
  eprint = {2606.28929},
  archiveprefix = {arXiv},
  primaryclass = {cs.CR},
  url = {https://arxiv.org/abs/2606.28929}
}