Nástroje boje proti hlasovým DeepFakes

Tools To Combat Voice DeepFakes

grant

Deepfakes; artificial intelligence; computer security

Deepfakes are a new application of artificial intelligence with a significant
impact on computer security. They are becoming easier than ever to create, and
these tools can be used to deceive individuals and organizations, especially when
combined with social engineering tactics such as phishing. 

This project therefore focuses on understanding the possible uses and associated
threats in the malicious use of deepfakes, with the intention of finding reliable
strategies to mitigate these threats. By doing so, we can ensure that these
innovations are used ethically and responsibly, creating a more sustainable and
fairer future for all. 

The project's activities are focused on 4 areas: improvement of the core
technology for speaker detection, development of technology for identification of
modified and artificially created voice, implementation of these technologies in
the systems of the Phonexia company and development of standardized testing of
the resistance of voice biometric systems to the mentioned threats. Testing will
take into account the current quality of methods for creating deepfakes in order
to ensure the highest possible robustness of the system.

Matějka Pavel, Ing., Ph.D. (DCGM) – research leader
Hanáček Petr, doc. Dr. Ing. (DITS)
Malinka Kamil, Mgr., Ph.D. (DITS)
Plchot Oldřich, Ing., Ph.D. (DCGM)