@article{falsesenseofsecuritywhyprobingbasedmalic,
  title = {False Sense of Security: Why Probing-based Malicious Input Detection Fails to Generalize},
  author = {Cheng Wang and Zeming Wei and Qin Liu and Muhao Chen},
  year = {2025},
  eprint = {2509.03888},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2509.03888},
}