Towards Mitigating Audio Adversarial Perturbations
نویسندگان
چکیده
Audio adversarial examples targeting automatic speech recognition systems have recently been made possible in different tasks, such as speech-to-text translation and speech classification. Here we aim to explore the robustness of these audio adversarial examples generated via two attack strategies by applying different signal processing methods to recover the original audio sequence. In addition, we also show that by inspecting the temporal consistency in speech signals, we can potentially identify non-adaptive audio adversarial examples considered in our experiments with a promising success rate.
منابع مشابه
Mitigating adversarial effects through randomization
Convolutional neural networks have demonstrated their powerful ability on various tasks in recent years. However, they are extremely vulnerable to adversarial examples. I.e., clean images, with imperceptible perturbations added, can easily cause convolutional neural networks to fail. In this paper, we propose to utilize randomization to mitigate adversarial effects. Specifically, we use two ran...
متن کاملDeepSafe: A Data-driven Approach for Checking Adversarial Robustness in Neural Networks
Deep neural networks have become widely used, obtaining remarkable results in domains such as computer vision, speech recognition, natural language processing, audio recognition, social network filtering, machine translation, and bio-informatics, where they have produced results comparable to human experts. However, these networks can be easily “fooled” by adversarial perturbations: minimal cha...
متن کاملTowards Robust Deep Neural Networks with BANG
Machine learning models, including state-of-the-art deep neural networks, are vulnerable to small perturbations that cause unexpected classification errors. This unexpected lack of robustness raises fundamental questions about their generalization properties and poses a serious concern for practical deployments. As such perturbations can remain imperceptible – commonly called adversarial exampl...
متن کاملNAG: Network for Adversary Generation
Adversarial perturbations can pose a serious threat for deploying machine learning systems. Recent works have shown existence of image-agnostic perturbations that can fool classifiers over most natural images. Existing methods present optimization approaches that solve for a fooling objective with an imperceptibility constraint to craft the perturbations. However, for a given classifier, they g...
متن کاملAdversarial Spheres
State of the art computer vision models have been shown to be vulnerable to small adversarial perturbations of the input. In other words, most images in the data distribution are both correctly classified by the model and are very close to a visually similar misclassified image. Despite substantial research interest, the cause of the phenomenon is still poorly understood and remains unsolved. W...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2018