基于WiFi的非入侵式异常用户活动检测

信息安全研究 ›› 2018, Vol. 4 ›› Issue (8): 711-714.

基于WiFi的非入侵式异常用户活动检测

庞娜

中国科学院信息工程研究所

收稿日期:2018-08-29 出版日期:2018-08-15 发布日期:2018-09-01
通讯作者: 庞娜
作者简介:庞娜博士研究生，主要研究方向为无线网络、人工智能． sunnypxn@163.com

Non-Invasive Abnormal Activity Detection Through WiFi Signals

Received:2018-08-29 Online:2018-08-15 Published:2018-09-01

摘要/Abstract

摘要： 移动互联网将移动通信和互联网结合，显著改变着人们的工作习惯，给人们的生活带来极大便利.无线局域网作为其重要组成部分，无线链路取代计算机和键盘之间的电缆，在安防领域有重要作用，可以实现重点场所人员、设备的识别、定位与跟踪.来自正交频分复用多个子载波的信道响应提供了详细的传输链路信息——信道状态信息，可用于检测和区分无线信道中的微小变化.总结了WiFi环境感知所面临的挑战，基于正交频分复用子载波的物理层信道状态信息提出异常用户活动检测方法.实验结果表明：该方法可在直线视距和非直线视距条件下有效地检测异常用户活动.

关键词: 信道状态信息, 无线通信, 物理层, 正交频分复用, 异常活动检测

Abstract: The mobile Internet combines mobile communications with the Internet, dramatically changing peoples working habits, and bringing great convenience to our life. As an important part of the wireless LAN, the wireless link replaces the cable between the computer and the keyboard. Wireless LANs play an important role in the field of security, which can realize the identification, positioning and tracking of personnel and equipment in key locations. The channel response from Orthogonal Frequency Division Multiplexing (OFDM) subcarriers has provided detailed transmission link information, Channel State Information (CSI), which can be used to detect and distinguish small changes in the wireless channel. This paper summarizes the challenges faced by the WiFi context awareness, and proposes an abnormal activity detection method based on the physical layer Channel State Information of Orthogonal Frequency Division Multiplexing (OFDM) subcarriers. The experimental results demonstrate that the abnormal activities can be automatically detected under both lineofsight (LOS) and nonlineofsight (NLOS) scenarios.

Key words: channel state information, wireless communication, physical layer, orthogonal frequency division multiplexing, abnormal activity detection

庞娜. 基于WiFi的非入侵式异常用户活动检测[J]. 信息安全研究, 2018, 4(8): 711-714.

参考文献

[1] Wang Y, Wu K, Ni L M. WiFall: device-Free fall detection by wireless networks[J]. IEEE Trans on Mobile Computing, 2017, 16(2):581-594 [2] Wang Y, Liu J, Chen Y, et al. E-eyes:Device-free location-oriented activity identification using fine-grained WiFi signatures[C]// Proc of Int Conf on Mobile Computing and Networking. New York: ACM, 2014:617-628 [3] Ali K, Liu A X, Wang W, et al. Keystroke recognition using WiFi signals[C]// Proc of Inte Conf on Mobile Computing & Networking. New York: ACM, 2015:90-102 [4] Halperin D, Hu W, Sheth A, et al. Tool release:gathering 802.11n traces with channel state information[J]. ACM SIGCOMM Computer Communication Review, 2011, 41(1):53-53 [5] Adib F, Kabelac Z, Katabi D, et al. 3d tracking via body radio reflections[C]// Proc of the 11th USENIX Symp on Networked Systems Design and Implementation. Berkeley: USENIX, 2014:317-329 [6] Kellogg B, Talla V, Gollakota S. Bringing gesture recognition to all devices[C]// Proc of USENIX Conf on Networked Systems Design and Implementation. Berkeley: USENIX, 2014:303-316 [7] Seifeldin M, Youssef M. A deterministic large-scale device-free passive localization system for wireless environments[C]// Proc of Int Conf on Pervasive Technologies Related to Assistive Environments. Piscataway, NJ: IEEE, 2010:1-8 [8] Sigg S, Shi S, Buesching F, et al. Leveraging RF-channel fluctuation for activity recognition: Active and passive systems, continuous and RSSI-based signal features[M]// Earth Observation of Global Change. 2013:109-14 [9] Wang G, Zou Y, Zhou Z, et al. We can hear you with Wi-Fi![C]// Proc of Int Conf on Mobile Computing and Networking. New York: ACM, 2014:593-604 [10] Zheng X, Wang J, Shangguan L, et al. Smokey: Ubiquitous smoking detection with commercial WiFi infrastructures[C]//Proc of IEEE Int Confrence on Computer Communications. Piscataway, NJ: IEEE, 2016:1-9