Related papers: Adversarial Learning for Improved Onsets and Frame…

Adversarial training (AT) is currently one of the most effective ways to obtain the robustness of deep neural networks against adversarial attacks. However, most AT methods suffer from robust overfitting, i.e., a significant generalization…

Adversarial attacks refer to a set of methods that perturb the input to a classification model in order to fool the classifier. In this paper we apply different gradient based adversarial attack algorithms on five deep learning models…

Recently, adversarial machine learning attacks have posed serious security threats against practical audio signal classification systems, including speech recognition, speaker recognition, and music copyright detection. Previous studies…

Adversarial training, in which a network is trained on both adversarial and clean examples, is one of the most trusted defense methods against adversarial attacks. However, there are three major practical difficulties in implementing and…

We propose a test-time defense mechanism against adversarial attacks: imperceptible image perturbations that significantly alter the predictions of a model. Unlike existing methods that rely on feature filtering or smoothing, which can lead…

As audio/visual classification models are widely deployed for sensitive tasks like content filtering at scale, it is critical to understand their robustness along with improving the accuracy. This work aims to study several key questions…

Adversarial examples tremendously threaten the availability and integrity of machine learning-based systems. While the feasibility of such attacks has been observed first in the domain of image processing, recent research shows that speech…

This paper addresses the problem of domain adaptation for the task of music source separation. Using datasets from two different domains, we compare the performance of a deep learning-based harmonic-percussive source separation model under…

Forecasting irregular time series presents significant challenges due to two key issues: the vulnerability of models to mean regression, driven by the noisy and complex nature of the data, and the limitations of traditional error-based…

Deep neural networks (DNNs) have achieved remarkable success in computer vision tasks such as image classification, segmentation, and object detection. However, they are vulnerable to adversarial attacks, which can cause incorrect…

Deep learning for medical imaging suffers from temporal and privacy-related restrictions on data availability. To still obtain viable models, continual learning aims to train in sequential order, as and when data is available. The main…

Training machine learning models that are robust against adversarial inputs poses seemingly insurmountable challenges. To better understand adversarial robustness, we consider the underlying problem of learning robust representations. We…

This paper presents a new semantic frame parsing model, based on Berkeley FrameNet, adapted to process spoken documents in order to perform information extraction from broadcast contents. Building upon previous work that had shown the…

Despite the success on few-shot learning problems, most meta-learned models only focus on achieving good performance on clean examples and thus easily break down when given adversarially perturbed samples. While some recent works have shown…

Modeling various aspects that make a music piece unique is a challenging task, requiring the combination of multiple sources of information. Deep learning is commonly used to obtain representations using various sources of information, such…

Neural Networks (NNs) are vulnerable to adversarial examples. Such inputs differ only slightly from their benign counterparts yet provoke misclassifications of the attacked NNs. The required perturbations to craft the examples are often…

Adversarial training is by far the most successful strategy for improving robustness of neural networks to adversarial attacks. Despite its success as a defense mechanism, adversarial training fails to generalize well to unperturbed test…

Current neural-network-based classifiers are susceptible to adversarial examples. The most empirically successful approach to defending against such adversarial examples is adversarial training, which incorporates a strong self-attack…

Anomaly detection is to identify samples that do not conform to the distribution of the normal data. Due to the unavailability of anomalous data, training a supervised deep neural network is a cumbersome task. As such, unsupervised methods…

Unsupervised domain adaptation, which involves transferring knowledge from a label-rich source domain to an unlabeled target domain, can be used to substantially reduce annotation costs in the field of object detection. In this study, we…