相关论文: Adversarial Black-Box Attacks on Automatic Speech …

Many speech enhancement methods try to learn the relationship between noisy and clean speech, obtained using an acoustic room simulator. We point out several limitations of enhancement methods relying on clean speech targets; the goal of…

We enhance the vanilla adversarial training method for unsupervised Automatic Speech Recognition (ASR) by a diffusion-GAN. Our model (1) injects instance noises of various intensities to the generator's output and unlabeled reference text…

Training robust deep learning models for down-stream tasks is a critical challenge. Research has shown that down-stream models can be easily fooled with adversarial inputs that look like the training data, but slightly perturbed, in a way…

In a transfer-based attack against Automatic Speech Recognition (ASR) systems, attacks are unable to access the architecture and parameters of the target model. Existing attack methods are mostly investigated in voice assistant scenarios…

We present a method for adversarial input generation against black box models for reading comprehension based question answering. Our approach is composed of two steps. First, we approximate a victim black box model via model extraction…

This paper addresses the challenge of integrating low-resource languages into multilingual automatic speech recognition (ASR) systems. We introduce a novel application of weighted cross-entropy, typically used for unbalanced datasets, to…

Deep neural networks (DNNs) are sensitive to adversarial data in a variety of scenarios, including the black-box scenario, where the attacker is only allowed to query the trained model and receive an output. Existing black-box methods for…

Multilingual training has been shown to improve acoustic modeling performance by sharing and transferring knowledge in modeling different languages. Knowledge sharing is usually achieved by using common lower-level layers for different…

Large language models (LLMs) are increasingly augmented with long-term memory systems to overcome finite context windows and enable persistent reasoning across interactions. However, recent research finds that LLMs become more vulnerable…

Many existing deep learning models are vulnerable to adversarial examples that are imperceptible to humans. To address this issue, various methods have been proposed to design network architectures that are robust to one particular type of…

Due to the development of machine learning and speech processing, speech emotion recognition has been a popular research topic in recent years. However, the speech data cannot be protected when it is uploaded and processed on servers in the…

Following the recent adoption of deep neural networks (DNN) accross a wide range of applications, adversarial attacks against these models have proven to be an indisputable threat. Adversarial samples are crafted with a deliberate intention…

As human-machine voice interfaces provide easy access to increasingly intelligent machines, many state-of-the-art automatic speech recognition (ASR) systems are proposed. However, commercial ASR systems usually have poor performance on…

Convolutional neural networks have outperformed humans in image recognition tasks, but they remain vulnerable to attacks from adversarial examples. Since these data are crafted by adding imperceptible noise to normal images, their existence…

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…

Machine learning models have been successfully applied to a wide range of applications including computer vision, natural language processing, and speech recognition. A successful implementation of these models however, usually relies on…

Deep learning (DL), despite its enormous success in many computer vision and language processing applications, is exceedingly vulnerable to adversarial attacks. We consider the use of DL for radio signal (modulation) classification tasks,…

Nowadays, digital facial content manipulation has become ubiquitous and realistic with the success of generative adversarial networks (GANs), making face recognition (FR) systems suffer from unprecedented security concerns. In this paper,…

Deep neural networks have been widely used in various downstream tasks, especially those safety-critical scenario such as autonomous driving, but deep networks are often threatened by adversarial samples. Such adversarial attacks can be…

Low resource automatic speech recognition (ASR) is a useful but thorny task, since deep learning ASR models usually need huge amounts of training data. The existing models mostly established a bottleneck (BN) layer by pre-training on a…