Katharina Prinz, Arthur Flexer,
"End-to-End Adversarial White Box Attacks on Music Instrument Classification"
, in arxiv.org, 2020
Original Titel:
End-to-End Adversarial White Box Attacks on Music Instrument Classification
Sprache des Titels:
Englisch
Original Kurzfassung:
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.
Sprache der Kurzfassung:
Englisch
Journal:
arxiv.org
Erscheinungsjahr:
2020
Anzahl der Seiten:
8
Reichweite:
international
Publikationstyp:
Aufsatz / Paper in Online-Archiv (nicht-referiert)
Forschungs-