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 difficult 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 limited 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 leverages 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.

Tiny spy cameras hidden in everyday objects are continuing to pose severe privacy threats to the general public as these cameras are often placed in sensitive locations such as hotels and restroom stalls. Commercially available "hidden camera detectors" have high false positive rates, and existing academic works detect (but cannot localize) only a subset of hidden cameras with wireless capabilities. We overcome these limitations by proposing LAPD, a novel hidden camera detection and localization system that leverages time-of-flight (ToF) sensors on commodity smartphones. LAPD is a smartphone app that detects hidden cameras in real-time by transmitting laser signals from the ToF sensor and searching for unique signatures representing reflections from hidden camera lenses. Using computer vision and machine learning techniques, LAPD achieves significantly higher hidden camera detection rates compared to the naked eye and hidden camera detectors.

Eavesdropping on private conversations is one of the most common yet detrimental threats to privacy. A number of recent works have explored side-channels on smart devices for recording sounds without permission. This paper presents LidarPhone, a novel acoustic side-channel attack through the lidar sensors equipped in popular commodity robot vacuum cleaners. The core idea is to repurpose the lidar to a laser-based microphone that can sense sounds from subtle vibrations induced on nearby objects. LidarPhone carefully processes and extracts traces of sound signals from inherently noisy laser reflections to capture privacy sensitive information (such as speech emitted by a victim's computer speaker as the victim is engaged in a teleconferencing meeting; or known music clips from television shows emitted by a victim's TV set, potentially leaking the victim's political orientation or viewing preferences). We implement LidarPhone on a Xiaomi Roborock vacuum cleaning robot and evaluate the feasibility of the attack through comprehensive real-world experiments. We use the prototype to collect both spoken digits and music played by a computer speaker and a TV soundbar, of more than 30k utterances totaling over 19 hours of recorded audio. LidarPhone achieves approximately 91% and 90% average accuracies of digit and music classifications, respectively.

Private conversations are an attractive target for malicious actors intending to conduct audio eavesdropping attacks. Previous works discovered unexpected vectors for these attacks, such as analyzing high-speed video of objects adjacent to sound sources, or using WiFi signal information. We propose LidarPhone, a novel side-channel attack that exploits the lidar sensors in commodity robot vacuum cleaners to perform acoustic eavesdropping attacks. LidarPhone is able to detect the minute vibrations induced on objects that are near audio sources, and extract meaningful signals from inherently noisy raw lidar returns. We evaluate a realistic scenario for potential victims: recovering privacy-sensitive digits (e.g., credit card numbers, social security numbers) emitted by computer speakers during teleconferencing calls. We implement LidarPhone on a Xiaomi Roborock vacuum cleaning robot and perform a comprehensive series of real-world experiments to determine its performance. LidarPhone achieves up to 91% accuracy for digit classification.