I have received my M.S. in Computer Sciences from the University of Wisconsin-Madison as well as my Diplôme d'Ingénieur (M.S. and B.S. in Engineering Sciences) from the French Engineering School École Centrale de Lyon. I also received a B.S. in General Mathematics and Applications from Claude Bernard Lyon 1 University.
My research interests are centered around building more secure and trustworthy Machine Learning models. More specifically, my interests focus on foundation models and how they can securely interact with systems.
Email: contact@jcnf.me
Address: 1210 W. Dayton St., Room 2263, Madison, WI 53706, USA
@inproceedings{zhao_libiht_2025,
address = {Taipei, Taiwan},
author = {Changyu Zhao and Yohan Beugin and Jean-Charles {Noirot Ferrand} and Quinn Burke and Guancheng Li and Patrick McDaniel},
booktitle = {Workshop on Software Understanding and Reverse Engineering (SURE)},
month = {October},
title = {{LibIHT}: A Hardware-Based Approach to Efficient and Evasion-Resistant Dynamic Binary Analysis},
year = {2025}
}
@inproceedings{li_robustness_2025,
author = {Kunyang Li and Jean-Charles {Noirot Ferrand} and Ryan Sheatsley and Blaine Hoak and Yohan Beugin and Eric Pauley and Patrick McDaniel},
booktitle = {IEEE/CVF International Conference on Computer Vision (ICCV)},
month = {October},
title = {On the {Robustness} {Tradeoff} in {Fine}-{Tuning}},
url = {https://arxiv.org/abs/2503.14836},
year = {2025}
}
@misc{domico2025adversarialagentsblackboxevasion,
archiveprefix = {arXiv},
author = {Kyle Domico and Jean-Charles {Noirot Ferrand} and Ryan Sheatsley and Eric Pauley and Josiah Hanna and Patrick McDaniel},
eprint = {2503.01734},
primaryclass = {cs.CR},
title = {Adversarial Agents: Black-Box Evasion Attacks with Reinforcement Learning},
url = {https://arxiv.org/abs/2503.01734},
year = {2025}
}
@misc{ferrand2025targetingalignmentextractingsafety,
archiveprefix = {arXiv},
author = {Jean-Charles {Noirot Ferrand} and Yohan Beugin and Eric Pauley and Ryan Sheatsley and Patrick McDaniel},
eprint = {2501.16534},
primaryclass = {cs.CR},
title = {Targeting Alignment: Extracting Safety Classifiers of Aligned LLMs},
url = {https://arxiv.org/abs/2501.16534},
year = {2025}
}