Research Reveals Gaming Mice Can Be Repurposed for Audio Eavesdropping via AI

Can your mouse spy on you? Research shows a high-sensitivity gaming mouse can pick up your speech with a malicious AI-driven trick
TechRadar

Key Points

  • High‑DPI gaming mice can detect desk vibrations caused by speech.
  • Researchers used Wiener filtering and AI to turn vibrations into intelligible audio.
  • The technique, called "Mic‑E‑Mouse," achieved about 80 % speaker‑recognition accuracy.
  • Successful exploitation requires malware that accesses the mouse sensor.
  • The attack could be used for corporate espionage or personal eavesdropping.
  • Standard security practices, such as updated antivirus and cautious software installation, can reduce risk.

A new research paper from University of California scholars demonstrates that high‑sensitivity gaming mice can capture acoustic vibrations from a desk, convert them into intelligible speech using signal‑processing techniques and artificial intelligence, and potentially be used for covert surveillance. The exploit, dubbed “Mic‑E‑Mouse,” requires a compromised PC and a mouse with DPI above 20,000. Tests showed a speaker‑recognition accuracy of about 80 percent, raising concerns about corporate espionage and personal privacy. Experts advise robust security practices to mitigate the risk.

How the Mic‑E‑Mouse Exploit Works

Researchers from the University of California have identified a novel side‑channel attack that leverages the ultra‑high sensitivity of modern gaming mice. These devices, often exceeding 20,000 DPI, can detect minute acoustic vibrations transmitted through the surface they rest on. When a user speaks, the resulting vibrations travel through the desk and are picked up by the mouse sensor.

The raw vibration data is not directly useful as audio, so the researchers applied a Wiener filtering process to clean the signal. After this preprocessing, a machine‑learning model enhances the audio, making spoken words audible. In demonstrations presented at ACSAC 2025, the system produced speech that, while digitized, was sufficiently clear for comprehension. The authors reported a speaker‑recognition accuracy of roughly 80 %.

Implications and Mitigation

To exploit this vector, an attacker must first compromise the victim’s computer with malware capable of accessing the mouse’s sensor data. Once installed, the malicious code can continuously record desk vibrations and forward the processed audio to the attacker. Because the required hardware—high‑DPI gaming mice—is inexpensive and increasingly common, the attack surface is wider than previously assumed.

Potential targets include corporate environments where sensitive conversations occur, as well as individual users who may be unaware that their peripheral could be weaponized. The researchers note that factors such as mouse pad thickness could affect performance, but the core vulnerability remains viable.

Mitigation strategies focus on standard security hygiene: maintaining up‑to‑date antivirus solutions, avoiding suspicious software downloads, and monitoring for unauthorized peripheral access. While the exploit is still in early research stages, its feasibility underscores the need for manufacturers and security professionals to consider unconventional side‑channel threats in future device designs.

#Mic‑E‑Mouse#gaming mouse#high DPI#AI surveillance#signal processing#University of California#ACSAC 2025#malware#PC security#corporate espionage
Generated with  News Factory -  Source: TechRadar

Also available in: