EarSpy Attack can use motion sensor data to leverage Android devices


A tech paper titled “EarSpy: Spying Caller Speech and Identity through Tiny Vibrations of Smartphone Ear Speakers” revealed how snoopers can exploit indoor-mounted motion sensors. android cell phones can help adversaries listen to the user’s conversations.

Surprising facts about motion sensors

A team of researchers from different universities, including Rutgers University, Texas A&M University, Temple University, New Jersey Institute of Technology and the University of Dayton, conducted the research.

The research team included Ahmed Tanvir Mahdad, Cong Shi, Zhengkun Ye, Tianming Zhao, Yan Wang, Yingying Chen and Nitesh Saxena.

Dubbing this side channel attack EarSpy, the researchers noted that motion sensors could be used to record reverberations from the speakers so the attacker could determine the identity and gender of the caller and eavesdrop on their conversations. private.

This research supported the hypothesis that eavesdropping by capturing data from motion sensors is possible.

How does EarSpy Attack help in spying?

The researchers wrote that the to study (PDF) was based on the belief that smartphones’ built-in motion sensors can allow attackers to collect data about indoor locations and touchscreen inputs while listening to audio conversations without needing explicit permissions before collect raw data.

Initially, they thought it was not possible to generate powerful vibrations through speakers to listen to user conversations. But during their research, the team realized that modern smartphones have high-quality stereo speakers and highly sensitive sensors that can detect finer vibrations.

Therefore, they ultimately determined the ideal environment for successful eavesdropping using various devices and techniques. They used several pre-recorded audio files, a third-party app to capture sensor data during the call simulation, and a machine learning algorithm to interpret the results.

search results

The team found that genre detection was 98.6% and speaker detection was accurate up to 92.6%. Additionally, they found up to 56.42% accurate speech detection. This proved the existence of a differentiation between speech characteristics in the accelerometer data that attackers can exploit for eavesdropping. EarSpy focused on gender recognition using data collected at 20 Hz, indicating that a lower sampling rate can allow attackers to determine the user’s gender.

EarSpy Attack can use motion sensor data to leverage Android devices
Overview of Loudspeaker Eavesdropping

How to prevent eavesdropping?

The researchers recommended limiting permissions to counter eavesdropping via sensor data so that third-party apps cannot record sensor data without the user’s permission. It should be noted that Android 13 does not allow 200Hz sensor data collection without user permission to prevent accidental data leaks.

Additionally, experts have suggested that mobile device makers should be careful about designing louder speakers and instead focus on maintaining similar sound pressure during audio conversations as was the case. case with the speakers of older generation phones.

Finally, positioning motion sensors as far away from the ear speaker as possible could minimize vibration from the phone’s speaker and decrease the chances of eavesdropping.

  1. 5 tips to protect your phone from malware
  2. 10 Android educational apps that collect the most user data
  3. SSID Stripping flaw allows hackers to imitate real wireless access points
  4. Hackers could access photos, videos without unlocking your phone