Tianhang Zhao
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Crypto×1
Frequent co-authors
Research Timeline
2026
GradSentry: Gradient Spectral Entropy for Backdoor Sample Filtering in Large Language Model Fine-Tuning
GradSentry introduces a novel backdoor sample filtering method that uses the spectral entropy of individual sample gradients to detect poisoned data during LLM fine-tuning, proving effective even at high poison ratios.
Highlighted terms show continued research focus across papers
Papers
cs.CRRecentMay 26, 2026
GradSentry: Gradient Spectral Entropy for Backdoor Sample Filtering in Large Language Model Fine-Tuning
Haodong Zhao, Tianyi Xu, Tianhang Zhao, Zhuosheng Zhang +1 more
GradSentry introduces a novel backdoor sample filtering method that uses the spectral entropy of individual sample gradients to detect poisoned data during LLM fine-tuning, proving effective even at h…
View →