MotionCompass

He, Yan Mary; He, Qiuye; Fang, Song; Liu, Yao

doi:10.1145/3458864.3467683

Cited by 11 publications

(3 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are also methods for detecting spy cameras through ML and traffic patterns [6], [7], [16]. Kevin Wu et al introduce a similarity analysis technique examining the timing characteristics of recorded video and network traffic from WiFi cameras [6].…”

Section: Related Workmentioning

confidence: 99%

“…MotionComp uses an Android application to detect the location of cameras using a new wireless camera localization technology. However, this approach has two limitations: it relies on MAC addresses from device manufacturer organizations to find wireless camera traffic, and it only works on cameras that provide motion detection features [7]. FindSpy uses a large amount of unlabeled data for pre-training, and then uses a NN-LSTM classifier to detect wireless cameras.…”

Section: Related Workmentioning

confidence: 99%

“…One approach involves comparing the recorded video to streaming network traffic and training a neural network to distinguish between normal and potentially suspicious camera signals [6]. Another method involves analyzing motion trajectories within a designated motion detection area to calculate the position of a camera [7]. However, the successful implementation of these techniques requires extensive data collection to effectively train the neural network [6].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Wireless Spy Camera Spotter System With Real-Time Traffic Similarity Analysis and WiFi Signal Tracing

An,

Park,

Park

2024

IEEE Access

View full text Add to dashboard Cite

This paper introduces a novel method to detect WiFi-enabled spy cameras potentially invading user privacy via wirelessly streaming within a user's vicinity. So far, there have been social initiatives to conduct spy camera inspections to address this issue, and academic societies have been working on various detection methods. However, such studies typically rely on additional specific efforts, such as using specialized equipment to gather channel state information (CSI) or collecting extensive long-term data per location for machine learning approaches. In addition, some ideas could not recognize features of spy camera data due to data encryption. Hence, this paper comes up with a novel scheme for detecting wireless spy camera only based on off-the-shelf devices. To achieve these functionalities, the proposed scheme consists of three phases: 1) classification, 2) detection, and 3) localization. First, in the classification phase, the collected packet headers are analyzed to identify and classify the upstream streaming protocols. In addition, the proposed scheme fulfills the detection phase that exploits the Nilsimsa algorithm to analyze packet similarity, identifying potential spy cameras by detecting consistent high similarity patterns in the classified data traffic. Finally, the proposed approach provides the localization phase that captures and analyzes Received Signal Strength Indication (RSSI) values at the target location and spots the camera position. Unlike existing methods, the proposed scheme does not rely on extensive data collection per location and complex mechanisms to interpret encrypted data. Moreover, compared to machine learning (ML)-based positioning means, which require significant data sets and long-term computation time, the scheme achieves real-time detection with minimal computational demands.

show abstract