IEEE Access (Jan 2024)
Real-Time Sensing and On-Site Spotting Scheme of Multi-Type WLAN Spycams
Abstract
This paper proposes a real-time sensing and on-site spotting scheme for multi-type wireless LAN based spy-cameras. The proposed scheme has the goal of overcoming the restrictions of previous studies on location-dependent training data per target location for spycam traffic classification and learning-based positioning, and the overhead requiring additional equipment to gather specific data for spycam location such as channel state information (CSI). In addition, some ways to send video data via spycams exploit data encryption, so it leads to erasing feature of video data which should be trained to the models for camera existence detection. In other words, there is a lack of comprehensive research that integrates the detection and localization of these surveillance video devices without reliance on data preparation per location and special devices. Recognizing the need to detect video devices used for such malicious purposes in real-time, this paper introduces a method that utilizes the Nilsimsa hashing algorithm and the Log-Distance Path Loss (LDPL) model for similarity checks to detect and localize various video devices transmitting wirelessly. We capture the wireless data transmitted and use the Nilsimsa hashing algorithm, which generates similar hash results for similar inputs, to detect video devices through similarity checks. Furthermore, we rely only on the recent signal strength indication (RSSI) values received to quickly estimate the location of the device that is not very accurate but detectable with eyes at the site, regardless of its type. Our approach shows determining the presence of a device within 3 seconds and estimating its approximate location with an average accuracy of approximately $0.08~{m}$ within a $1~{m}$ range and $0.45~{m}$ within a $3~{m}$ range, regardless of the device type.
Keywords
