This article discusses how machine learning techniques can improve acoustic eavesdropping attacks using gyroscopes and accelerometers in smartphones. It highlights recent research that bypasses the need for microphone access by utilizing these sensors to extract speech data. The series will explore the success of previous projects and attempt to reproduce and enhance their results.

Vulnerabilities in a Bluetooth chipset used in 29 audio devices from various vendors can be exploited for eavesdropping and information theft. Researchers disclosed three flaws that allow attackers to hijack connections, initiate calls, and potentially access call history and contacts, although attacks require technical expertise and close physical proximity. Device manufacturers are working on patches, but many affected devices have not yet received updates.