相关论文: Deep Adversarial Learning on Google Home devices

Deep reinforcement learning (RL) policies are known to be vulnerable to adversarial perturbations to their observations, similar to adversarial examples for classifiers. However, an attacker is not usually able to directly modify another…

Although deep neural networks have shown promising performances on various tasks, even achieving human-level performance on some, they are shown to be susceptible to incorrect predictions even with imperceptibly small perturbations to an…

Speaker recognition systems (SRSs) have recently been shown to be vulnerable to adversarial attacks, raising significant security concerns. In this work, we systematically investigate transformation and adversarial training based defenses…

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…

Deep learning models are known to solve classification and regression problems by employing a number of epoch and training samples on a large dataset with optimal accuracy. However, that doesn't mean they are attack-proof or unexposed to…

Deep learning (DL) is becoming popular as a new tool for many applications in wireless communication systems. However, for many classification tasks (e.g., modulation classification) it has been shown that DL-based wireless systems are…

Deep learning has made significant breakthroughs in many fields, including electroencephalogram (EEG) based brain-computer interfaces (BCIs). However, deep learning models are vulnerable to adversarial attacks, in which deliberately…

Machine Learning models are vulnerable to adversarial attacks that rely on perturbing the input data. This work proposes a novel strategy using Autoencoder Deep Neural Networks to defend a machine learning model against two gradient-based…

Due to their massive success in various domains, deep learning techniques are increasingly used to design network intrusion detection solutions that detect and mitigate unknown and known attacks with high accuracy detection rates and…

Privacy preservation has long been a concern in smart acoustic monitoring systems, where speech can be passively recorded along with a target signal in the system's operating environment. In this study, we propose the integration of two…

Deep learning takes advantage of large datasets and computationally efficient training algorithms to outperform other approaches at various machine learning tasks. However, imperfections in the training phase of deep neural networks make…

Deep Learning has empowered us to train neural networks for complex data with high performance. However, with the growing research, several vulnerabilities in neural networks have been exposed. A particular branch of research, Adversarial…

Machine learning is a powerful tool enabling full automation of a huge number of tasks without explicit programming. Despite recent progress of machine learning in different domains, these models have shown vulnerabilities when they are…

On-device deep learning is rapidly gaining popularity in mobile applications. Compared to offloading deep learning from smartphones to the cloud, on-device deep learning enables offline model inference while preserving user privacy.…

Recently, opportunities to transmit speech data to deep learning models executed in the cloud have increased. This has led to growing concerns about speech privacy, including both speaker-specific information and the linguistic content of…

The rapid progress in personalized speech generation technology, including personalized text-to-speech (TTS) and voice conversion (VC), poses a challenge in distinguishing between generated and real speech for human listeners, resulting in…

Automatic speech recognition (ASR) systems are known to be vulnerable to adversarial attacks. This paper addresses detection and defence against targeted white-box attacks on speech signals for ASR systems. While existing work has utilised…

Data augmentation (DA) has gained widespread popularity in deep speaker models due to its ease of implementation and significant effectiveness. It enriches training data by simulating real-life acoustic variations, enabling deep neural…

Deep neural networks have been demonstrated to be vulnerable to adversarial noise, promoting the development of defense against adversarial attacks. Motivated by the fact that adversarial noise contains well-generalizing features and that…

The discovery of adversarial examples has raised concerns about the practical deployment of deep learning systems. In this paper, we demonstrate that adversarial examples are capable of manipulating deep learning systems across three…