titleGradSentry: Gradient Spectral Entropy for Backdoor Sample Filtering in Large Language Model Fine-Tuning
authorsHaodong Zhao, Tianyi Xu, Tianhang Zhao, Zhuosheng Zhang, Gongshen Liu
date2026-05-26
venuearXiv (preprint, not peer reviewed)
idarXiv:2605.26574
affiliationShanghai Jiao Tong University
upvotes9 (Hugging Face Daily Papers, 2026-11-01)
linksabs pdf hf code
abstractFine-tuning Large Language Models with untrusted data exposes models to backdoor attacks, where poisoned samples cause targeted misbehavior. Existing sample-filtering defenses rely on clustering, which requires sufficient data and can fail at extreme poison ratios. We propose GradSentry ({Grad}ient {Sentry}), a backdoor sample filtering method based on the spectral entropy of per-sample gradients. Our key finding is that poisoned samples produce gradients with higher spectral entropy compared to clean samples. GradSentry captures output-altering backdoor signatures using per-sample gradient spectra, avoiding pairwise sample comparisons and clustering during feature construction. Importantly, our method is training-agnostic: it works for both parameter-efficient fine-tuning methods like LoRA and full-parameter tuning, as the gradient analysis operates independently of which parameters are being updated during training. GradSentry requires no clustering, operates effectively across all poison ratios (1%--90%), and introduces minimal computational overhead (20-50ms per sample for 7B model). Evaluation on four QA datasets and four attack types demonstrates the effectiveness of spectral entropy for backdoor detection. Code is available at https://github.com/dongdongzhaoUP/GradSentry.

cite

@misc{zhao2026gradsentry,
  title={GradSentry: Gradient Spectral Entropy for Backdoor Sample Filtering in Large Language Model Fine-Tuning},
  author={Haodong Zhao and Tianyi Xu and Tianhang Zhao and Zhuosheng Zhang and Gongshen Liu},
  year={2026},
  eprint={2605.26574},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2605.26574}
}