Showing 2024Show all
2 papers · 1 filter
cs.SD2024
DistriBlock: Identifying adversarial audio samples by leveraging characteristics of the output distribution
MatÃas Pizarro, Dorothea Kolossa, Asja Fischer
Adversarial attacks can mislead automatic speech recognition (ASR) systems into predicting an arbitrary target text, thus posing a clear security threat. To prevent such attacks, w…
eess.AS2024
Robustifying automatic speech recognition by extracting slowly varying features
MatÃas Pizarro, Dorothea Kolossa, Asja Fischer
In the past few years, it has been shown that deep learning systems are highly vulnerable under attacks with adversarial examples. Neural-network-based automatic speech recognition…