郑州大学学报（理学版）2025，Vol.57Issue(6)：65-73,82,10.DOI:10.13705/j.issn.1671-6841.2024077
基于长短周期特征的用户异常行为检测
Abnormal User Behavior Detection Based on Long-term and Short-term Characteristics
摘要
Abstract
With the increasing number and types of users,the energy big data platform is now facing prominent internal security threats.User abnormal behavior detection is an effective technique to resist such security threats.However,current mainstream detection approaches did not take behavior pattern of different types of users in the same platform and their long-term and short-term behavior characteristics in-to consideration,therefore leading to low user abnormal behavior detection performance.To solve these challenges,a method was proposed to extract the long-term and short-term behavior characteristics of dif-ferent users in the energy big data platform.Specifically,the long short periods isolated forest model and the multiple time windows gate recurrent neural network were proposed to construct the long-term and short-term user behavior patterns respectively,and then the results of two models were effectively integrat-ed for better detection ability.Moreover,an abnormal behavior detection framework was constructed with the consideration of different platform user types.Finally,the proposed framework was verified in a pro-vincial energy big data platform,and the experimental results showed that our framework effectively char-acterized different user behavior patterns in this platform and achieved a high accuracy of abnormal user behavior detection as well as high processing efficiency.关键词
用户行为/异常行为检测/长周期特征/短周期特征Key words
user behavior/abnormal behavior detection/long-term characteristics/short-term character-istics分类
信息技术与安全科学引用本文复制引用
王世谦,白宏坤,贾一博,卜飞飞,黄勇..基于长短周期特征的用户异常行为检测[J].郑州大学学报（理学版）,2025,57(6):65-73,82,10.基金项目
国网河南省电力公司2023年度科技项目(5217L022001A) （5217L022001A）
