EchoLLM: LLM-Augmented Acoustic Eavesdropping Attack on Bone Conduction Headphones with mmWave Radar
Xin Yao
34th USENIX Security Symposium (USENIX Security '25) · Day 3 · Privacy 3: Attacks
The proliferation of bone conduction headphones, lauded for their open-ear design and suitability for active lifestyles, has inadvertently introduced a novel and significant privacy vulnerability. This talk, "EchoLLM: LLM-Augmented Acoustic Eavesdropping Attack on Bone Conduction Headphones with mmWave Radar," presented by Xin Yao, unveils a sophisticated eavesdropping technique that leverages cutting-edge millimeter-wave (mmWave) radar technology combined with the advanced capabilities of Large Language Models (LLMs) to reconstruct private conversations. The research highlights how the inherent mechanism of bone conduction – transmitting sound through vibrations – can be exploited to inadvertently leak sensitive information, from passwords to confidential discussions.
AI review
Legitimate academic security research that crosses a genuinely novel attack surface — bone conduction headphone vibration exfiltration via mmWave radar, with LLM-assisted ASR to push WER into practical territory. The fusion of physical-layer side-channel work with modern ML pipelines is the real contribution here, and the $930 hardware budget makes the threat model credible rather than theoretical.