Certo, bisogna prima addestrare il modello e sapere quale rumore corrisponde a quale lettera, ma una volta che si ha il modello…
Ad esempio, facendo document sharing e registrando l’audio si potrebbe capire quale suono corrisponde a quale lettera e poi, quando non c’e’ il document sharing, e uno inserisce una password…
Usate un password manager! (io uso keepass XC) e in azienda usate un riconoscimento biometrico senza trattamento di dati personali tipo questo.
Site: Arxiv
With recent developments in deep learning, the ubiquity of micro-phones and the rise in online services via personal devices, acoustic side channel attacks present a greater threat to keyboards than ever. This paper presents a practical implementation of a state-of-the-art deep learning model in order to classify laptop keystrokes, using a smartphone integrated microphone. When trained on keystrokes recorded by a nearby phone, the classifier achieved an accuracy of 95%, the highest accuracy seen without the use of a language model. When trained on keystrokes recorded using the video-conferencing software Zoom, an accuracy of 93% was achieved, a new best for the medium. Our results prove the practicality of these side channel attacks via off-the-shelf equipment and algorithms. We discuss a series of mitigation methods to protect users against these series of attacks.
Continua qui: [2308.01074] A Practical Deep Learning-Based Acoustic Side Channel Attack on Keyboards
