1 citations · 1 across the 4 of their papers we have counts for
Showing cs.CRShow all
2 papers · 1 filter
cs.CR2026
GradSentry: Gradient Spectral Entropy for Backdoor Sample Filtering in Large Language Model Fine-Tuning
Haodong Zhao, Tianyi Xu, Tianhang Zhao +2
Fine-tuning Large Language Models with untrusted data exposes models to backdoor attacks, where poisoned samples cause targeted misbehavior. Existing sample-filtering defenses rely…
cs.CR2025
Patronus: Identifying and Mitigating Transferable Backdoors in Pre-trained Language Models
Tianhang Zhao, Haodong Zhao, Wei Du +5
The ``Pre-train, then fine-tune'' paradigm has revolutionized Natural Language Processing (NLP). In this context, transferable backdoors pose a severe threat to the Pre-trained Lan…