@article{safetynetdetectingharmfuloutputsinllms,
  title = {SafetyNet: Detecting Harmful Outputs in LLMs by Modeling and Monitoring Deceptive Behaviors},
  author = {Maheep Chaudhary and Fazl Barez},
  year = {2025},
  eprint = {2505.14300},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.14300v1},
}