11 citations · 32 across the 35 of their papers we have counts for
11 papers · 1 filter
Gracefully Filtering Backdoor Samples for Generative Large Language Models without Retraining
Zongru Wu, Pengzhou Cheng, Lingyong Fang +2
Backdoor attacks remain significant security threats to generative large language models (LLMs). Since generative LLMs output sequences of high-dimensional token logits instead of…
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…
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…
Flooding Spread of Manipulated Knowledge in LLM-Based Multi-Agent Communities
Tianjie Ju, Yiting Wang, Xinbei Ma +7
The rapid adoption of large language models (LLMs) in multi-agent systems has highlighted their impressive capabilities in various applications, such as collaborative problem-solvi…
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…
MKF-ADS: Multi-Knowledge Fusion Based Self-supervised Anomaly Detection System for Control Area Network
Pengzhou Cheng, Zongru Wu, Gongshen Liu
Control Area Network (CAN) is an essential communication protocol that interacts between Electronic Control Units (ECUs) in the vehicular network. However, CAN is facing stringent…
How Large Language Models Encode Context Knowledge? A Layer-Wise Probing Study
Tianjie Ju, Weiwei Sun, Wei Du +3
Previous work has showcased the intriguing capability of large language models (LLMs) in retrieving facts and processing context knowledge. However, only limited research exists on…
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…
Acquiring Clean Language Models from Backdoor Poisoned Datasets by Downscaling Frequency Space
Zongru Wu, Zhuosheng Zhang, Pengzhou Cheng +1
Despite the notable success of language models (LMs) in various natural language processing (NLP) tasks, the reliability of LMs is susceptible to backdoor attacks. Prior research a…
Investigating Multi-Hop Factual Shortcuts in Knowledge Editing of Large Language Models
Tianjie Ju, Yijin Chen, Xinwei Yuan +4
Recent work has showcased the powerful capability of large language models (LLMs) in recalling knowledge and reasoning. However, the reliability of LLMs in combining these two capa…
R-Judge: Benchmarking Safety Risk Awareness for LLM Agents
Tongxin Yuan, Zhiwei He, Lingzhong Dong +9
Large language models (LLMs) have exhibited great potential in autonomously completing tasks across real-world applications. Despite this, these LLM agents introduce unexpected saf…