8 citations · 19 across the 38 of their papers we have counts for
Showing 2026 · cs.CRShow all
3 papers · 2 filters
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.CR2026
EmbTracker: Traceable Black-box Watermarking for Federated Language Models
Haodong Zhao, Jinming Hu, Yijie Bai +6
Federated Language Model (FedLM) allows a collaborative learning without sharing raw data, yet it introduces a critical vulnerability, as every untrustworthy client may leak the re…
cs.CR2026
ProtegoFed: Backdoor-Free Federated Instruction Tuning with Interspersed Poisoned Data
Haodong Zhao, Jinming Hu, Zhaomin Wu +7
Federated Instruction Tuning (FIT) enables collaborative instruction tuning of large language models across multiple organizations (clients) in a cross-silo setting without requiri…