Sriram Sami National University of Singapore
Sean Rui Xiang Tan National University of Singapore
Bangjie Sun National University of Singapore
Jun Han∗ Yonsei Univerity
ABSTRACT Tiny hidden spy cameras concealed in sensitive locations including hotels and bathrooms are becoming a significant threat worldwide. These hidden cameras are easily purchasable and are extremely dif- ficult to find with the naked eye due to their small form factor. The state-of-the-art solutions that aim to detect these cameras are lim- ited as they require specialized equipment and yield low detection rates. Recent academic works propose to analyze the wireless traffic that hidden cameras generate. These proposals, however, are also limited because they assume wireless video streaming, while only being able to detect the presence of the hidden cameras, and not their locations. To overcome these limitations, we present LAPD, a novel hidden camera detection and localization system that lever- ages the time-of-flight (ToF) sensor on commodity smartphones. We implement LAPD as a smartphone app that emits laser signals from the ToF sensor, and use computer vision and machine learning techniques to locate the unique reflections from hidden cameras. We evaluate LAPD through comprehensive real-world experiments by recruiting 379 participants and observe that LAPD achieves an 88.9% hidden camera detection rate, while using just the naked eye yields only a 46.0% hidden camera detection rate.
CCS CONCEPTS • Human-centered computing → Mobile computing; • Com- puter systems organization → Sensors and actuators.
KEYWORDS Time-of-Flight, Hidden Camera, Smartphone
ACM Reference Format: Sriram Sami, Sean Rui Xiang Tan, Bangjie Sun, and Jun Han. 2021. LAPD: Hidden Spy Camera Detection using Smartphone Time-of-Flight Sensors. In The 19th ACM Conference on Embedded Networked Sensor Systems (SenSys ’21), November 15–17, 2021, Coimbra, Portugal. ACM, New York, NY, USA, 14 pages. https://doi.org/10.1145/3485730.3485941
∗Corresponding author.
SenSys ’21, November 15–17, 2021, Coimbra, Portugal © 2021 Copyright held by the owner/author(s). ACM ISBN 978-1-4503-9097-2/21/11. https://doi.org/10.1145/3485730.3485941
Figure 1: Figure depicts a user operating a smartphone run- ning the LAPD app. LAPD emits laser pulses from the smart- phone’s time-of-flight (ToF) sensor, and detects reflections from a hidden camera concealed in a water bottle. LAPD an- notates the location of the hidden camera on the screen.
1 INTRODUCTION Tiny hidden spy cameras placed in sensitive locations such as hotel rooms and lavatories are increasingly a threat to individual privacy globally [31, 33, 53, 67, 81, 97]. For example, in South Korea alone, there were over 6,800 such reported cases in a single year [22, 65, 69]. These hidden cameras are difficult to detect due to their small form factors, with lens diameters as small as 1 – 2 millimeters [22, 69, 75, 87]. Consequently, the general public is left vulnerable and generally relies on the authorities to find these cameras [60].
The state-of-the-art solutions to assist authorities and the general public to detect and localize hidden cameras are commercial “hidden camera detectors” [61, 85]. A user looking through a detector’s viewfinder observes bright reflections from nearby camera lenses due to the red light emitted from LEDs on the detector. While more effective than the naked eye, the users must carry such devices with them. In addition, the detectors exhibit high false positives from reflective surfaces [21].
In attempts to overcome the limitations of the state-of-the-art detectors, recent academic works propose to detect the presence of hidden cameras by analyzing the wireless traffic they generate [15, 16, 44, 48, 57, 78, 91, 92]. However, these techniques bear two
288
This work is licensed under a Creative Commons Attribution International 4.0 License.