Deep Learning, Audio Adversaries, and Music Content Analysis |
Corey Kereliuk, Bob L. Sturm, Jan Larsen
|
| Abstract | We present the concept of adversarial audio in the context of deep
neural networks (DNNs) for music content analysis. An adversary
is an algorithm that makes minor perturbations to an input that cause
major repercussions to the system response. In particular, we design
an adversary for a DNN that takes as input short-time spectral magnitudes
of recorded music and outputs a high-level music descriptor.
We demonstrate how this adversary can make the DNN behave in
any way with only extremely minor changes to the music recording
signal. We show that the adversary cannot be neutralised by a
simple filtering of the input. Finally, we discuss adversaries in the
broader context of the evaluation of music content analysis systems. |
| Keywords | deep nural networks, music information retrieval |
| Type | Conference paper [With referee] |
| Conference | 2015 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics |
| Year | 2015 Month October |
| Publisher | IEEE |
| Note | October 18-21, 2015, New Paltz, NY |
| Electronic version(s) | [pdf] |
| Publication link | http://www.waspaa.com/ |
| BibTeX data | [bibtex] |
| IMM Group(s) | Intelligent Signal Processing |