Katharina Prinz, Arthur Flexer,
"End-to-End Adversarial White Box Attacks on Music Instrument Classification"
, in arXiv.org, 2020, ISSN: 2331-8422
End-to-End Adversarial White Box Attacks on Music Instrument Classification
Sprache des Titels:
Small adversarial perturbations of input data are able to
drastically change performance of machine learning systems, thereby challenging the validity of such systems. We
present the very first end-to-end adversarial attacks on a
music instrument classification system allowing to add perturbations directly to audio waveforms instead of spectrograms. Our attacks are able to reduce the accuracy close to
a random baseline while at the same time keeping perturbations almost imperceptible and producing misclassifications to any desired instrument.