activity
20232026
most citedHow Large Language Models Encode Context Knowledge? A Layer-Wise Probing Study

4 citations · 4 across the 6 of their papers we have counts for

collaborators
Showing cs.CRShow all

6 papers · 1 filter

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.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…

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

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…

cs.CR2023

Backdoor Attacks and Countermeasures in Natural Language Processing Models: A Comprehensive Security Review

Pengzhou Cheng, Zongru Wu, Wei Du +3

Language Models (LMs) are becoming increasingly popular in real-world applications. Outsourcing model training and data hosting to third-party platforms has become a standard metho…