Return
Advancing text adversarial example generation using large language models
DOI:10.1016/j.knosys.2025.114361.png)
Abstract
En 中文
• Novel method for generating text adversarial examples for machine learning models. • Adversarial examples achieved by utilizing recent large language models. • Facilitates systematic vulnerability analysis and improvement of model robustness. • Promising results in attacking recent open-weight large language models.
Keywords:
Adversarial attack
Text adversarial example
Large language model
Natural language processing
Text classification
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
K
IF:
7.6
Papers:
1.2W
Citations:
4.5W
Organization
No organization information available

