相关论文: DolphinAtack: Inaudible Voice Commands

Speech models are often trained on sensitive data in order to improve model performance, leading to potential privacy leakage. Our work considers noise masking attacks, introduced by Amid et al. 2022, which attack automatic speech…

Audio watermarking embeds auxiliary information into speech while maintaining speaker identity, linguistic content, and perceptual quality. Although recent advances in neural and digital signal processing-based watermarking methods have…

Thanks to the popularisation of transformer-based models, speech recognition (SR) is gaining traction in various application fields, such as industrial and robotics environments populated with mission-critical devices. While…

Due to the popularity of Artificial Intelligence (AI) technology, numerous backdoor attacks are designed by adversaries to mislead deep neural network predictions by manipulating training samples and training processes. Although backdoor…

Speech deepfakes are artificial voices generated by machine learning models. Previous literature has highlighted deepfakes as one of the biggest security threats arising from progress in artificial intelligence due to their potential for…

Automatic Speech Recognition (ASR) systems convert speech into text and can be placed into two broad categories: traditional and fully end-to-end. Both types have been shown to be vulnerable to adversarial audio examples that sound benign…

Traditional control interfaces for robotic-assisted minimally invasive surgery impose a significant cognitive load on surgeons. To improve surgical efficiency, surgeon-robot collaboration capabilities, and reduce surgeon burden, we present…

The cloud-based speech recognition/API provides developers or enterprises an easy way to create speech-enabled features in their applications. However, sending audios about personal or company internal information to the cloud, raises…

Machine learning (ML) models are known to be vulnerable to adversarial examples. Applications of ML to voice biometrics authentication are no exception. Yet, the implications of audio adversarial examples on these real-world systems remain…

In the past few years, it has been shown that deep learning systems are highly vulnerable under attacks with adversarial examples. Neural-network-based automatic speech recognition (ASR) systems are no exception. Targeted and untargeted…

With the thriving of deep learning and the widespread practice of using pre-trained networks, backdoor attacks have become an increasing security threat drawing many research interests in recent years. A third-party model can be poisoned in…

An automatic speech recognition (ASR) system based on a deep neural network is vulnerable to attack by an adversarial example, especially if the command-dependent ASR fails. A defense method against adversarial examples is proposed to…

Dysarthric speech recognition (DSR) enhances the accessibility of smart devices for dysarthric speakers with limited mobility. Previously, DSR research was constrained by the fact that existing datasets typically consisted of isolated…

Earables (ear wearables) is rapidly emerging as a new platform encompassing a diverse range of personal applications. The traditional authentication methods hence become less applicable and inconvenient for earables due to their limited…

This paper introduces mmWave-Whisper, a system that demonstrates the feasibility of full-corpus automated speech recognition (ASR) on phone calls eavesdropped remotely using off-the-shelf frequency modulated continuous wave (FMCW)…

The Apple operating system (iOS) has so far proved resistant to information-hiding techniques, which help attackers covertly communicate. However, Siri - a native iOS service that controls iPhones and iPads via voice commands - could change…

In low-resource computing contexts, such as smartphones and other tiny devices, Both deep learning and machine learning are being used in a lot of identification systems. as authentication techniques. The transparent, contactless, and…

The modern generative audio models can be used by an adversary in an unlawful manner, specifically, to impersonate other people to gain access to private information. To mitigate this issue, speech deepfake detection (SDD) methods started…

In the audio modality, state-of-the-art watermarking methods leverage deep neural networks to allow the embedding of human-imperceptible signatures in generated audio. The ideal is to embed signatures that can be detected with high accuracy…

Current adversarial attacks against speaker recognition systems (SRSs) require either white-box access or heavy black-box queries to the target SRS, thus still falling behind practical attacks against proprietary commercial APIs and…