29 citations · 92 across the 18 of their papers we have counts for
21 papers
Protecting Publicly Available Data With Machine Learning Shortcuts
Nicolas M. Müller, Maximilian Burgert, Pascal Debus +3
Machine-learning (ML) shortcuts or spurious correlations are artifacts in datasets that lead to very good training and test performance but severely limit the model's generalizatio…
Complex-valued neural networks for voice anti-spoofing
Nicolas M. Müller, Philip Sperl, Konstantin Böttinger
Current anti-spoofing and audio deepfake detection systems use either magnitude spectrogram-based features (such as CQT or Melspectrograms) or raw audio processed through convoluti…
Introducing Model Inversion Attacks on Automatic Speaker Recognition
Karla Pizzi, Franziska Boenisch, Ugur Sahin +1
Model inversion (MI) attacks allow to reconstruct average per-class representations of a machine learning (ML) model's training data. It has been shown that in scenarios where each…
Localized Shortcut Removal
Nicolas M. Müller, Jochen Jacobs, Jennifer Williams +1
Machine learning is a data-driven field, and the quality of the underlying datasets plays a crucial role in learning success. However, high performance on held-out test data does n…
Does Audio Deepfake Detection Generalize?
Nicolas M. Müller, Pavel Czempin, Franziska Dieckmann +2
Current text-to-speech algorithms produce realistic fakes of human voices, making deepfake detection a much-needed area of research. While researchers have presented various techni…
Language Dependencies in Adversarial Attacks on Speech Recognition Systems
Karla Markert, Donika Mirdita, Konstantin Böttinger
Automatic speech recognition (ASR) systems are ubiquitously present in our daily devices. They are vulnerable to adversarial attacks, where manipulated input samples fool the ASR s…