@ARTICLE\{IMM2015-06904,
author = "C. Kereliuk and B. L. Sturm and J. Larsen",
title = "Deep Learning and Music Adversaries",
year = "2015",
month = "nov",
keywords = "deep nural networks, music information retrieval, content based processing, pattern recognition and claasicificastion",
journal = "{IEEE} Transactions on Multimedia",
volume = "",
editor = "",
number = "",
publisher = "IEEE",
note = "Aeepar in 'Deep Learning for Multimedia Computing' special section",
url = "http://www2.imm.dtu.dk/pubdb/p.php?6904",
abstract = "An adversary is essentially an algorithm intent on
making a classification system perform in some particular way
given an input, e.g., increase the probability of a false negative.
Recent work builds adversaries for deep learning systems applied
to image object recognition, which exploits the parameters of
the system to find the minimal perturbation of the input image
such that the network misclassifies it with high confidence. We
adapt this approach to construct and deploy an adversary of
deep learning systems applied to music content analysis. In our
case, however, the input to the systems is magnitude spectral
frames, which requires special care in order to produce valid
input audio signals from network-derived perturbations. For two
different train-test partitionings of two benchmark datasets, and
two different deep architectures, we find that this adversary is
very effective in defeating the resulting systems. We find the
convolutional networks are more robust, however, compared with
systems based on a majority vote over individually classified
audio frames. Furthermore, we integrate the adversary into the
training of new deep systems, but do not find that this improves
their resilience against the same adversary.",
isbn_issn = "{DOI} 10.1109/TMM.2015.2478068"
}