信息安全研究2025，Vol.11Issue(8)：718-726,9.DOI:10.12379/j.issn.2096-1057.2025.08.05
基于知识增强多任务学习的隐式有害文本检测技术研究
Implicit Harmful Text Detection Technology Based on Knowledge-enhanced Multi-task Learning
摘要
Abstract
A large number of harmful texts on the Internet adopt implicit and euphemistic expressions to evade detection by censorship systems.Most of the current work focuses on explicit harmful speech and cannot effectively detect implicit harmful text.This paper investigates the detection of implicit euphemistic harmful text in Chinese using a multi-task learning approach,where euphemistic sentence recognition is used to assist harmful text detection.Firstly,methods for integrating euphemistic language vocabulary features are explored to enhance the model's representation of implicit meanings.Subsequently,contrastive learning is applied to enhance latent semantic representations and extract common features from implicitly harmful discourse.Finally,a multi-task learning framework is constructed by combining euphemistic sentence recognition tasks with harmful text detection tasks,aiming to improve the detection performance through shared multi-task parameters and multi-feature fusion loss functions.The experimental results demonstrate the effectiveness of the model in detecting implicit harmful text.关键词
隐性有害文本/委婉语/多任务学习/提示学习/对比学习Key words
implicit harmful text/euphemism/multi-task learning/prompt learning/contrastive learning分类
信息技术与安全科学引用本文复制引用
陈雅宁,柯亮,王文贤,陈兴蜀,王海舟..基于知识增强多任务学习的隐式有害文本检测技术研究[J].信息安全研究,2025,11(8):718-726,9.基金项目
国家重点研发计划项目(2022YFC3303101) （2022YFC3303101）
