activity
20232026
most citedStructured Chemistry Reasoning with Large Language Models

8 citations · 19 across the 38 of their papers we have counts for

collaborators
Showing cs.CRShow all

7 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.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…

cs.CR2024

NSmark: Null Space Based Black-box Watermarking Defense Framework for Language Models

Haodong Zhao, Jinming Hu, Peixuan Li +6

Language models (LMs) have emerged as critical intellectual property (IP) assets that necessitate protection. Although various watermarking strategies have been proposed, they rema…

cs.CR2024

Transferring Backdoors between Large Language Models by Knowledge Distillation

Pengzhou Cheng, Zongru Wu, Tianjie Ju +2

Backdoor Attacks have been a serious vulnerability against Large Language Models (LLMs). However, previous methods only reveal such risk in specific models, or present tasks transf…

cs.CR2024★ 5 cited

TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models

Pengzhou Cheng, Yidong Ding, Tianjie Ju +5

Large language models (LLMs) have raised concerns about potential security threats despite performing significantly in Natural Language Processing (NLP). Backdoor attacks initially…

cs.CR2024

SynGhost: Invisible and Universal Task-agnostic Backdoor Attack via Syntactic Transfer

Pengzhou Cheng, Wei Du, Zongru Wu +4

Although pre-training achieves remarkable performance, it suffers from task-agnostic backdoor attacks due to vulnerabilities in data and training mechanisms. These attacks can tran…