11 citations · 32 across the 35 of their papers we have counts for
9 papers · 1 filter
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…
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…
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…
GhostEI-Bench: Do Mobile Agents Resilience to Environmental Injection in Dynamic On-Device Environments?
Chiyu Chen, Xinhao Song, Yunkai Chai +7
Vision-Language Models (VLMs) are increasingly deployed as autonomous agents to navigate mobile graphical user interfaces (GUIs). Operating in dynamic on-device ecosystems, which i…
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…
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…
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…
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…