《计算机应用》唯一官方网站 ›› 2021, Vol. 41 ›› Issue (12): 3620-3625.DOI: 10.11772/j.issn.1001-9081.2021061115

• 第十八届中国机器学习会议(CCML 2021) • 上一篇    

基于局部敏感布隆过滤器的工业物联网隐性异常检测

肖如良1,2,3, 曾智霞1, 肖晨凯1,2, 张仕1,2()   

  1. 1.福建师范大学 计算机与网络空间安全学院,福州 350117
    2.数字福建环境监测物联网实验室(福建师范大学),福州 350117
    3.福建省网络安全与密码技术重点实验室(福建师范大学),福州 350007
  • 收稿日期:2021-05-12 修回日期:2021-08-18 接受日期:2021-08-31 发布日期:2021-12-28 出版日期:2021-12-10
  • 通讯作者: 张仕
  • 作者简介:肖如良(1966—),男,湖南娄底人,教授,博士生导师,博士,CCF高级会员,主要研究方向:机器学习、智能系统软件工程
    曾智霞(1998—),女,福建莆田人,主要研究方向:机器学习、异常检测
    肖晨凯(1995—),男,福建龙岩人,硕士,主要研究方向:机器学习、异常检测;
  • 基金资助:
    国家自然科学基金资助项目(61772004);福建省科技计划重大项目(2020H6011);福建省自然科学基金资助项目(2020J01161)

IIoT hidden anomaly detection based on locality sensitive Bloom filter

Ruliang XIAO1,2,3, Zhixia ZENG1, Chenkai XIAO1,2, Shi ZHANG1,2()   

  1. 1.College of Computer and Cyber Security,Fujian Normal University,Fuzhou Fujian 350117,China
    2.Digit Fujian Internet-of-Things Laboratory of Environmental Monitoring (Fujian Normal University),Fuzhou Fujian 350117,China.
    3.Fujian Provincial Key Lab of Network Security and Cryptology (Fujian Normal University),Fuzhou Fujian 350007,China
  • Received:2021-05-12 Revised:2021-08-18 Accepted:2021-08-31 Online:2021-12-28 Published:2021-12-10
  • Contact: Shi ZHANG
  • About author:XIAO Ruliang, born in 1966, Ph. D., professor. His research interests include machine learning, intelligent system software engineering.
    ZENG Zhixia, born in 1998. Her research interests include machine learning, anomaly detection.
    XIAO Chenkai, born in 1995, M. S. His research interests include machine learning, anomaly detection.
  • Supported by:
    the National Natural Science Foundation of China(61772004);the Major Project of Fujian Province Science and Technology Plan(2020H6011);the Natural Science Foundation of Fujian Province(2020J01161)

摘要:

工业物联网(IIoT)系统中的传感器由于持续使用和正常磨损出现损坏,导致收集和记录的传感数据出现隐性异常。为解决该问题,提出一种基于局部敏感Bloom Filter(LSBF)模型的异常检测算法LSBFAD。首先利用基于空间划分的快速Johnson-Lindenstrauss变换(SP-FJLT)对数据进行哈希映射,然后采用相互竞争(MC)策略进行除噪,最后利用0-1编码构建Bloom Filter。在SIFT、MNIST和FMA三个基准数据集上进行的仿真实验中,LSBFAD算法的误报率(FAR)均低于10%。实验结果表明,基于LSBF的异常检测算法与当前主流的异常检测算法相比,具有较高的检测率(RD)和较低的误报率,可有效应用于IIoT数据的异常检测。

关键词: 工业物联网, 异常检测, 布隆过滤器, 快速Johnson-Lindenstrauss变换, 相互竞争策略, 隐性异常

Abstract:

Damage to sensors in Industrial Internet of Things (IIoT) system due to continuous use and normal wear leads to hidden anomalies in the collected and recorded sensing data. To solve this problem, an anomaly detection algorithm based on Local Sensitive Bloom Filter (LSBF) model was proposed, namely LSBFAD. Firstly, the Spatial Partition based Fast Johnson-Lindenstrauss Transform (SP-FJLT) was used to perform hash mapping to the data, then the Mutual Competition (MC) strategy was used to reduce noise, and finally the Bloom filter was constructed by 0-1 coding. In simulation experiments conducted on three benchmark datasets including SIFT, MNIST and FMA, the false detection rate of LSBFAD algorithm is less than 10%. Experimental results show that compared with the current mainstream anomaly detection algorithms, the proposed anomaly detection algorithm based on LSBF has higher Detection Rate (DR) and lower False Alarm Rate (FAR) and can be effectively applied to anomaly detection of IIoT data.

Key words: Industrial Internet of Things (IIoT), anomaly detection, Bloom filter, fast Johnson-Lindenstrauss transform, Mutual Competition (MC) strategy, hidden anomaly

中图分类号: