A survey on voice assistant security: Attacks and countermeasures
Voice assistants (VA) have become prevalent on a wide range of personal devices such as
smartphones and smart speakers. As companies build voice assistants with extra …
smartphones and smart speakers. As companies build voice assistants with extra …
Adversarial attacks and defenses for deep-learning-based unmanned aerial vehicles
J Tian, B Wang, R Guo, Z Wang… - IEEE Internet of Things …, 2021 - ieeexplore.ieee.org
The introduction of deep learning (DL) technology can improve the performance of cyber–
physical systems (CPSs) in many ways. However, this also brings new security issues. To …
physical systems (CPSs) in many ways. However, this also brings new security issues. To …
Black-box adversarial attacks on commercial speech platforms with minimal information
Adversarial attacks against commercial black-box speech platforms, including cloud speech
APIs and voice control devices, have received little attention until recent years. Constructing …
APIs and voice control devices, have received little attention until recent years. Constructing …
Can we use arbitrary objects to attack lidar perception in autonomous driving?
As an effective way to acquire accurate information about the driving environment, LiDAR
perception has been widely adopted in autonomous driving. The state-of-the-art LiDAR …
perception has been widely adopted in autonomous driving. The state-of-the-art LiDAR …
Veriml: Enabling integrity assurances and fair payments for machine learning as a service
Machine Learning as a Service (MLaaS) allows clients with limited resources to outsource
their expensive ML tasks to powerful servers. Despite the huge benefits, current MLaaS …
their expensive ML tasks to powerful servers. Despite the huge benefits, current MLaaS …
Hear sign language: A real-time end-to-end sign language recognition system
Sign language recognition (SLR) bridges the communication gap between the hearing-
impaired and the ordinary people. However, existing SLR systems either cannot provide …
impaired and the ordinary people. However, existing SLR systems either cannot provide …
Query-efficient adversarial attack with low perturbation against end-to-end speech recognition systems
S Wang, Z Zhang, G Zhu, X Zhang… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
With the widespread use of automated speech recognition (ASR) systems in modern
consumer devices, attack against ASR systems have become an attractive topic in recent …
consumer devices, attack against ASR systems have become an attractive topic in recent …
Study of pre-processing defenses against adversarial attacks on state-of-the-art speaker recognition systems
Adversarial examples are designed to fool the speaker recognition (SR) system by adding a
carefully crafted human-imperceptible noise to the speech signals. Posing a severe security …
carefully crafted human-imperceptible noise to the speech signals. Posing a severe security …
{KENKU}: Towards Efficient and Stealthy Black-box Adversarial Attacks against {ASR} Systems
Prior researchers show that existing automatic speech recognition (ASR) systems are
vulnerable to adversarial examples. Most existing adversarial attacks against ASR systems …
vulnerable to adversarial examples. Most existing adversarial attacks against ASR systems …
LinkBreaker: Breaking the backdoor-trigger link in DNNs via neurons consistency check
Backdoor attacks cause model misbehaving by first implanting backdoors in deep neural
networks (DNNs) during training and then activating the backdoor via samples with triggers …
networks (DNNs) during training and then activating the backdoor via samples with triggers …