@article{compromisinghonestyandharmlessnessin,
  title = {Compromising Honesty and Harmlessness in Language Models via Deception Attacks},
  author = {Laurène Vaugrante and Francesca Carlon and Maluna Menke and Thilo Hagendorff},
  year = {2025},
  eprint = {2502.08301},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2502.08301v2},
}