- AI can now reconstruct speech through concrete using only a portable pops not -skoved microphone lines
- Laptop microphone cables double as antennas, delicious sound through radio harmonics
- MEMS microphones emit signals that betray private conversations without system comprois or malware
A new form of eavesdropping uses artificial intelligence to recover speech from devices through walls.
A report from EENEWS Overview, how it utilizes a vulnerability in widely used MEMS (microelectromechanical systems) microphones, and the most affected devices are laptops, partly because of their internal wiring design.
Researchers from the University of Florida and Japan’s University of Electro Communication demonstrated even through a 25 cm concrete barrier, attackers can accurately reconstruct speech using nothing but an FM receiver, a copper antenna and machine learning tools.
So why laptops?
The microphones in many laptops are connected via long, unprotected wires, which effectively turns them into antennas, the researchers note.
“With an FM radio receiver and a copper antenna you can intercept these microphones. That’s how easy this can be … It costs maybe a hundred dollars or even less,” said Professor Sara Rampazzi at the University of Florida.
The research revealed an accuracy of up to 94.2% by recognizing spoken digits, while Openai’s generative models achieved a transcription error percentage as low as 6.5%.
The researchers examined several MEMS microphones, including MP34DT01 m from Stmicroelectronics, Knowles SPM0405 (now Synaptics), TDK Invense CS-41350 and T3902 and VPERS VM3000 (now part of Qualcomm).
These microphones emit electromagnetic signals that can leak acoustic data through radio harmonics.
According to Stmicroelectronics, “This is an inherent behavior of digital PDM MEMS microphones,” and the design used in laptops often lacks shielding that transforms flat cables into ideal antennas.
To mitigate this risk, experts recommend moving microphones within laptops to reduce cable length and shielding of the wires. They also suggest using scattered spectrum clock to reduce the understanding of emissions without affecting the benefit.
These corrections are relatively simple, but they are relevant to newer devices that move on. What about already existing devices?
Regular users need to invest in the best antivirus or end point protection solutions that offer some protection, even if they are not explicitly listed to defend against this new threat.
These tools typically work at the software level and may not detect passive attacks that do not involve code execution or system compris.
For individuals seeking the protection of the best identity theft, this research shows that even conversations assumed to be private can be within reach of sophisticated, cheap surveillance.
