@article{whenbenchmarkslieevaluatingmaliciousprom,
  title = {When Benchmarks Lie: Evaluating Malicious Prompt Classifiers Under True Distribution Shift},
  author = {Max Fomin},
  year = {2026},
  eprint = {2602.14161},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2602.14161},
}