Národní úložiště šedé literatury Nalezeno 1 záznamů.  Hledání trvalo 0.01 vteřin. 
Resilience of Biometric Authentication of Voice Assistants Against Deepfakes
Kaška, Petr ; Pleško, Filip (oponent) ; Malinka, Kamil (vedoucí práce)
Voice assistants (Apple Siri, Amazon Alexa, Google-assistant, Samsung Bixby) supporting voice control offer more and more possibilities to make all our daily activities easier. People give them access to data and information to take full advantage of all these features. Along with the rapidly developing voice deepfake technology, there is a big threat in the area of misusing deepfakes to trick smart voice assistants. An attacker can record the victim's voice, synthesize the voice and create a recording of some command to trick the assistant in order to harm the victim. The aim of this work is to design an experiment that will simulate attacks, performed by synthetic voice, on voice assistants and then evaluate their defensiveness. The conducted experiment confirms the initial hypothesis of the vulnerability of voice assistants to deepfake attacks and the results are very alarming with an overall success rate of 90% indicating insufficient defense of voice assistants and require the implementation of additional countermeasures to prevent the risk of misuse as the number of voice assistants in active use is rapidly increasing.

Viz též: podobná jména autorů
5 KAŠKA, Pavel
5 Kaška, Pavel
Chcete být upozorněni, pokud se objeví nové záznamy odpovídající tomuto dotazu?
Přihlásit se k odběru RSS.