相关论文: Trade-offs Between Capacity and Robustness in Neur…

In realistic environments, speech is usually interfered by various noise and reverberation, which dramatically degrades the performance of automatic speech recognition (ASR) systems. To alleviate this issue, the commonest way is to use a…

Automatic Speaker Verification (ASV), increasingly used in security-critical applications, faces vulnerabilities from rising adversarial attacks, with few effective defenses available. In this paper, we propose a neural codec-based…

There has been a recent surge in adversarial attacks on deep learning based automatic speech recognition (ASR) systems. These attacks pose new challenges to deep learning security and have raised significant concerns in deploying ASR…

Deep neural networks are vulnerable to adversarial attacks, which can fool them by adding minuscule perturbations to the input images. The robustness of existing defenses suffers greatly under white-box attack settings, where an adversary…

This paper explores the integration of model-based and data-driven approaches within the realm of neural speech and audio coding systems. It highlights the challenges posed by the subjective evaluation processes of speech and audio codecs…

Sensitivity to adversarial noise hinders deployment of machine learning algorithms in security-critical applications. Although many adversarial defenses have been proposed, robustness to adversarial noise remains an open problem. The most…

Residual Vector Quantization (RVQ) has become a dominant approach in neural speech and audio coding, providing high-fidelity compression. However, speech coding presents additional challenges due to real-world noise, which degrades…

In recent years, significant progress has been made in deep model-based automatic speech recognition (ASR), leading to its widespread deployment in the real world. At the same time, adversarial attacks against deep ASR systems are highly…

Deep learning models can be fooled by small $l_p$-norm adversarial perturbations and natural perturbations in terms of attributes. Although the robustness against each perturbation has been explored, it remains a challenge to address the…

Adversarial attack methods have demonstrated the fragility of deep neural networks. Their imperceptible perturbations are frequently able fool classifiers into potentially dangerous misclassifications. We propose a novel way to interpret…

Deep neural networks are incredibly vulnerable to crafted, human-imperceptible adversarial perturbations. Although adversarial training (AT) has proven to be an effective defense approach, we find that the AT-trained models heavily rely on…

We propose a novel data-dependent structured gradient regularizer to increase the robustness of neural networks vis-a-vis adversarial perturbations. Our regularizer can be derived as a controlled approximation from first principles,…

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…

The fact that deep neural networks are susceptible to crafted perturbations severely impacts the use of deep learning in certain domains of application. Among many developed defense models against such attacks, adversarial training emerges…

The adversarial attacks against deep neural networks on computer vision tasks have spawned many new technologies that help protect models from avoiding false predictions. Recently, word-level adversarial attacks on deep models of Natural…

In light of the widespread application of Automatic Speech Recognition (ASR) systems, their security concerns have received much more attention than ever before, primarily due to the susceptibility of Deep Neural Networks. Previous studies…

Adversarial robustness refers to a model's ability to resist perturbation of inputs, while distribution robustness evaluates the performance of the model under data shifts. Although both aim to ensure reliable performance, prior work has…

Neural speech codecs have demonstrated their ability to compress high-quality speech and audio by converting them into discrete token representations. Most existing methods utilize Residual Vector Quantization (RVQ) to encode speech into…

A key challenge for Deep Neural Network (DNN) algorithms is their vulnerability to adversarial attacks. Inherently non-deterministic compute substrates, such as those based on Analog In-Memory Computing (AIMC), have been speculated to…

Deep neural networks (DNNs) are powerful nonlinear architectures that are known to be robust to random perturbations of the input. However, these models are vulnerable to adversarial perturbations--small input changes crafted explicitly to…