The success of machine learning is fueled by the increasing availability of computing power
and large training datasets. The training data is used to learn new models or update existing …

Backdoor attack intends to embed hidden backdoors into deep neural networks (DNNs), so
that the attacked models perform well on benign samples, whereas their predictions will be …

Voice Recognition Systems (VRSs) employ deep learning for speech recognition and
speaker recognition. They have been widely deployed in various real-world applications …

Speech recognition systems driven by Deep Neural Networks (DNNs) have revolutionized
human-computer interaction through voice interfaces, which significantly facilitate our daily …

Deep neural networks (DNNs) have been widely and successfully adopted and deployed in
various applications of speech recognition. Recently, a few works revealed that these …

Speech recognition systems, trained and updated based on large-scale audio data, are
vulnerable to backdoor attacks that inject dedicated triggers in system training. The used …

As asynchronous event data is more frequently engaged in various vision tasks, the risk of
backdoor attacks becomes more evident. However, research into the potential risk …

This work explores stylistic triggers for backdoor attacks in the audio domain: dynamic
transformations of malicious samples through guitar effects. We first formalize stylistic …

Voice assistant applications have become omniscient nowadays. Two models that provide
the two most important functions for real-life applications (ie, Google Home, Amazon Alexa …

Deep learning has achieved significant breakthroughs in speaker recognition, driven by
continual advancements in foundation models. However, malicious third-party platforms …