@article{detectinginstructionfinetuningattackon,
  title = {Detecting Instruction Fine-tuning Attack on Language Models with Influence Function},
  author = {Jiawei Li},
  year = {2025},
  eprint = {2504.09026},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2504.09026v1},
}