相关论文: Universal Adversarial Perturbations Generative Net…

Increasing shape-bias in deep neural networks has been shown to improve robustness to common corruptions and noise. In this paper we analyze the adversarial robustness of texture and shape-biased models to Universal Adversarial…

Generative Adversarial Networks have become one of the most studied frameworks for unsupervised learning due to their intuitive formulation. They have also been shown to be capable of generating convincing examples in limited domains, such…

Neural networks are vulnerable to adversarially-constructed perturbations of their inputs. Most research so far has considered perturbations of a fixed magnitude under some $l_p$ norm. Although studying these attacks is valuable, there has…

The paper presents a novel approach of spoofing wireless signals by using a general adversarial network (GAN) to generate and transmit synthetic signals that cannot be reliably distinguished from intended signals. It is of paramount…

Adversarial perturbations in speech pose a serious threat to automatic speech recognition (ASR) and speaker verification by introducing subtle waveform modifications that remain imperceptible to humans but can significantly alter system…

In recent years, Generative Adversarial Networks (GANs) have become a hot topic among researchers and engineers that work with deep learning. It has been a ground-breaking technique which can generate new pieces of content of data in a…

We present an algorithm for computing class-specific universal adversarial perturbations for deep neural networks. Such perturbations can induce misclassification in a large fraction of images of a specific class. Unlike previous methods…

Generative adversarial nets (GAN) has been successfully introduced for generating text to alleviate the exposure bias. However, discriminators in these models only evaluate the entire sequence, which causes feedback sparsity and mode…

Despite their impressive performance, deep neural networks (DNNs) are widely known to be vulnerable to adversarial attacks, which makes it challenging for them to be deployed in security-sensitive applications, such as autonomous driving.…

Deep learning-based time series models are being extensively utilized in engineering and manufacturing industries for process control and optimization, asset monitoring, diagnostic and predictive maintenance. These models have shown great…

Training deep neural networks on well-understood dependencies in speech data can provide new insights into how they learn internal representations. This paper argues that acquisition of speech can be modeled as a dependency between random…

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…

Distributed learning frameworks, which partition neural network models across multiple computing nodes, enhance efficiency in collaborative edge-cloud systems, but may also introduce new vulnerabilities to evasion attacks, often in the form…

Modern Voice Control Systems (VCS) rely on the collaboration of Automatic Speech Recognition (ASR) and Speaker Recognition (SR) for secure interaction. However, prior adversarial attacks typically target these tasks in isolation,…

Recent advances in Deep Learning show the existence of image-agnostic quasi-imperceptible perturbations that when applied to `any' image can fool a state-of-the-art network classifier to change its prediction about the image label. These…

An adversarial attack is an exploitative process in which minute alterations are made to natural inputs, causing the inputs to be misclassified by neural models. In the field of speech recognition, this has become an issue of increasing…

Deep learning models achieve excellent performance in numerous machine learning tasks. Yet, they suffer from security-related issues such as adversarial examples and poisoning (backdoor) attacks. A deep learning model may be poisoned by…

Deep neural network based speaker recognition systems can easily be deceived by an adversary using minuscule imperceptible perturbations to the input speech samples. These adversarial attacks pose serious security threats to the speaker…

Producing a large annotated speech corpus for training ASR systems remains difficult for more than 95% of languages all over the world which are low-resourced, but collecting a relatively big unlabeled data set for such languages is more…

Given a state-of-the-art deep neural network classifier, we show the existence of a universal (image-agnostic) and very small perturbation vector that causes natural images to be misclassified with high probability. We propose a systematic…