Syntactic paraphrase-based synthetic data generation for backdoor attacks against Chinese language models
Authors:
- Man HuMHMan Hu
- Yatao YangYYYatao Yang
- Deng PanDPDeng Pan
- Zhongliang GuoZGZhongliang Guo
- Luwei XiaoLXLuwei Xiao
- Deyu LinDLDeyu Lin
- Shuai ZhaoSZShuai Zhao
- 12 June 2025
- journal article
- Published by Elsevier in Information Fusion
- Vol. 124
Abstract
No abstract availableFunding Information
- Natural Science Foundation of Beijing Municipality (4232034)
- Fundamental Research Funds for the Central Universities (3282024058, 3282024052)
This publication has 28 references indexed in Scilit:
- Cross-Modal Knowledge Diffusion-Based Generation for Difference-Aware Medical VQAIEEE Transactions on Image Processing, 2025
- Clean-label backdoor attack and defense: An examination of language model vulnerabilityExpert Systems with Applications, 2024
- Has multimodal learning delivered universal intelligence in healthcare? A comprehensive surveyInformation Fusion, 2024
- Exploring Clean Label Backdoor Attacks and Defense in Language ModelsIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2024
- Red Alarm for Pre-trained Models: Universal Vulnerability to Neuron-level Backdoor AttacksMachine Intelligence Research, 2023
- Automatic Generation of Adversarial Readable Chinese TextsIEEE Transactions on Dependable and Secure Computing, 2022
- Mitigating backdoor attacks in LSTM-based text classification systems by Backdoor Keyword IdentificationNeurocomputing, 2021
- Design and Evaluation of a Multi-Domain Trojan Detection Method on Deep Neural NetworksIEEE Transactions on Dependable and Secure Computing, 2021
- Pre-trained models for natural language processing: A surveyScience China Technological Sciences, 2020
- A Backdoor Attack Against LSTM-Based Text Classification SystemsIEEE Access, 2019