Lei Che

Dr. Lei Che


Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
31 May 2025 in Electronics
Verified
Journal Article
Open access
PDF file
LCLei Che
Lei Che
CWChengcong Wu
Chengcong Wu
YHYan Hou
Yan Hou
This study aims to effectively defend against complex and diverse adversarial attacks, enhance adversarial defense performance in the field of textual adversarial examples, and address existing issues in current defense methods such as models’ inability to accurately detect perturbations and perform effective error correction. To this end, we propose a Large Language Model Adversarial Defense (LLMAD) method based on perturbation detection and correction. The LLMAD framework consists of two modules: a perturbation detection module and a perturbation correction module. The detection module combines pre-trained models with soft-masking layers to rapidly determine whether samples contain adversarial perturbations. The correction module employs large language models fine-tuned using an adversarial example perturbation dataset constructed through data augmentation, enhancing task performance in adversarial defense and enabling efficient and accurate error correction of adversarial samples. Experimental results demonstrate that, across multiple datasets, various target models defended through the LLMAD method achieve satisfactory defense effectiveness against different types of adversarial attacks. The classification accuracy of defended models shows an average improvement of 66.8% compared to undefended baselines and outperforms existing methods by 13.4% on average. Additional perturbation detection performance tests and ablation studies further validate the accuracy of detection capabilities and the effectiveness of module combinations. A series of experiments confirm that the LLMAD method can significantly enhance defensive effectiveness against textual adversarial attacks.

8 March 2017 in MATEC Web of Conferences
Verified
Journal Article
Open access
PDF file
LCLei Che
Lei Che
XYXiaoping Yang
Xiaoping Yang
FJFan Jiang
Fan Jiang
MATEC Web of Conferences, open access proceedings in Materials science, Engineering and Chemistry

30 August 2025
Verified
Book Chapter
Closed access
PDF file
HZHongrui Zhang
Hongrui Zhang
LCLei Che
Lei Che
LLLeilei Li
Leilei Li
JRJunling Ren
Junling Ren

1 February 2014 in Applied Mechanics and Materials
Verified
Journal Article
Closed access
LCLei Che
Lei Che
XYXiao Ping Yang
Xiao Ping Yang

24 April 2026 in Journal of Computational Methods in Sciences and Engineering
Verified
Journal Article
Closed access
LCLei Che
Lei Che