Jean-Charles Noirot Ferrand

Recent & Selected Publications

• Extracting the Harmfulness Classifier of Aligned LLMs
  Jean-Charles Noirot Ferrand, Patrick McDaniel
  Master Thesis, 2024
  PDF Cite

  @mastersthesis{noirot_ferrand_extracting_2024,
   author = {Jean-Charles {Noirot Ferrand} and Patrick McDaniel},
   booktitle = {Master Thesis},
   month = {December},
   school = {University of Wisconsin-Madison},
   title = {{Extracting} {the} {Harmfulness} {Classifier} {of} {Aligned} {LLMs}},
   url = {static/publications/ms_thesis_2024.pdf},
   year = {2024}
  }
  

• The Efficacy of Transformer-Based Adversarial Attacks in Security Domains
  Kunyang Li, Kyle D Domico, Jean-Charles Noirot Ferrand, Patrick McDaniel
  MILCOM 2023 - Workshop on Artificial Intelligence for Cyber (MILCOM 2023 - Workshop on AI for Cyber), 2023
  PDF Cite

  @inproceedings{Li2310:Efficacy,
   address = {Boston, USA},
   author = {Kunyang Li and Kyle D Domico and Jean-Charles {Noirot Ferrand} and Patrick McDaniel},
   booktitle = {MILCOM 2023 - Workshop on Artificial Intelligence for Cyber (MILCOM 2023 -
  Workshop on AI for Cyber)},
   days = {30},
   month = {October},
   pages = {6},
   title = {The Efficacy of {Transformer-Based} Adversarial Attacks in Security Domains},
   url = {https://arxiv.org/abs/2310.11597},
   year = {2023}
  }