Related papers: On the human evaluation of audio adversarial examp…
Adversarial examples are inputs to machine learning models designed by an adversary to cause an incorrect output. So far, adversarial examples have been studied most extensively in the image domain. In this domain, adversarial examples can…
Adversarial examples are inputs intentionally perturbed with the aim of forcing a machine learning model to produce a wrong prediction, while the changes are not easily detectable by a human. Although this topic has been intensively studied…
Speech is a common and effective way of communication between humans, and modern consumer devices such as smartphones and home hubs are equipped with deep learning based accurate automatic speech recognition to enable natural interaction…
It has been shown recently that deep learning based models are effective on speech quality prediction and could outperform traditional metrics in various perspectives. Although network models have potential to be a surrogate for complex…
Machine learning (ML) models are known to be vulnerable to adversarial examples. Applications of ML to voice biometrics authentication are no exception. Yet, the implications of audio adversarial examples on these real-world systems remain…
Natural Language Processing (NLP) models based on Machine Learning (ML) are susceptible to adversarial attacks -- malicious algorithms that imperceptibly modify input text to force models into making incorrect predictions. However,…
Machine learning systems based on deep neural networks, being able to produce state-of-the-art results on various perception tasks, have gained mainstream adoption in many applications. However, they are shown to be vulnerable to…
We propose a method to generate audio adversarial examples that can attack a state-of-the-art speech recognition model in the physical world. Previous work assumes that generated adversarial examples are directly fed to the recognition…
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…
The rise of machine-learning systems that process sensory input has brought with it a rise in comparisons between human and machine perception. But such comparisons face a challenge: Whereas machine perception of some stimulus can often be…
Adversarial examples seem to be inevitable. These specifically crafted inputs allow attackers to arbitrarily manipulate machine learning systems. Even worse, they often seem harmless to human observers. In our digital society, this poses a…
Computational paralinguistic analysis is increasingly being used in a wide range of cyber applications, including security-sensitive applications such as speaker verification, deceptive speech detection, and medical diagnostics. While…
We evaluate machine comprehension models' robustness to noise and adversarial attacks by performing novel perturbations at the character, word, and sentence level. We experiment with different amounts of perturbations to examine model…
Adversarial examples are carefully crafted attack points that are supposed to fool machine learning classifiers. In the last years, the field of adversarial machine learning, especially the study of perturbation-based adversarial examples,…
Audio processing models based on deep neural networks are susceptible to adversarial attacks even when the adversarial audio waveform is 99.9% similar to a benign sample. Given the wide application of DNN-based audio recognition systems,…
We demonstrate the existence of universal adversarial perturbations, which can fool a family of audio classification architectures, for both targeted and untargeted attack scenarios. We propose two methods for finding such perturbations.…
Adversarial examples (AEs) are crafted by adding human-imperceptible perturbations to inputs such that a machine-learning based classifier incorrectly labels them. They have become a severe threat to the trustworthiness of machine learning.…
Neural networks have demonstrated state-of-the-art performance in various machine learning fields. However, the introduction of malicious perturbations in input data, known as adversarial examples, has been shown to deceive neural network…
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…
Recent studies have highlighted audio adversarial examples as a ubiquitous threat to state-of-the-art automatic speech recognition systems. Thorough studies on how to effectively generate adversarial examples are essential to prevent…