Lamphone: Real-Time Passive Reconstruction of Speech Using Light Emitted from Lamps

Lamphone is a new method of eavesdropping that uses light bulbs to recover sound waves from a room. The technology is still in development but poses a potential threat to privacy.

• Lamphone uses electro-optical sensors to detect sound waves that cause vibrations in light bulbs
• The technology is still in development but has the potential to be a practical method of eavesdropping
• Advanced filtering techniques can be used to filter noise from the signal
• The use of deep learning to train a model for filtering noise comes with a cost
• The development of Lamphone is similar to the development of Gyrophone, which took six years to become a practical method of eavesdropping
• Scientists are likely to continue improving Lamphone in the coming years

Lamphone is a new technology that uses light bulbs to recover sound waves from a room. The technology is still in development, but it has the potential to be a practical method of eavesdropping. The development of Lamphone is similar to the development of Gyrophone, which took six years to become a practical method of eavesdropping. Scientists are likely to continue improving Lamphone in the coming years, which could pose a potential threat to privacy.

Recent studies have suggested various side-channel attacks for eavesdropping sound by analyzing the side effects of sound waves on nearby objects (e.g., a bag of chips and window) and devices (e.g., motion sensors). These methods pose a great threat to privacy, however they are limited in one of the following ways: they (1) cannot be applied in real time (e.g., Visual Microphone), (2) are not external, requiring the attacker to compromise a device with malware (e.g., Gyrophone), or (3) are not passive, requiring the attacker to direct a laser beam at an object (e.g., laser microphone). In this talk, I introduce "Lamphone," a novel side-channel attack for eavesdropping sound; this attack is performed by using a remote electro-optical sensor to analyze a hanging light bulb’s frequency response to sound. I show how fluctuations in the air pressure on the surface of the hanging bulb (in response to sound), which cause the bulb to vibrate very slightly (a millidegree vibration), can be exploited by eavesdroppers to recover speech and singing, passively, externally, and in real time. I analyze a hanging bulb’s response to sound via an electro-optical sensor and learn how to isolate the audio signal from the optical signal. Based on our analysis, I develop an algorithm to recover sound from the optical measurements obtained from the vibrations of a light bulb and captured by the electro-optical sensor. I evaluate Lamphone’s performance in a realistic setup and show that Lamphone can be used by eavesdroppers to recover human speech (which can be accurately identified by the Google Cloud Speech API) and singing (which can be accurately identified by Shazam and SoundHound) from a bridge located 25 meters away from the target room containing the hanging light bulb.