相关论文: On the Feasibility of Acoustic Attacks Using Commo…

Communication among microscopic robots (nanorobots) can coordinate their activities for biomedical tasks. The feasibility of in vivo ultrasonic communication is evaluated for micron-size robots broadcasting into various types of tissues.…

Automatic speech recognition (ASR) provides diverse audio-to-text services for humans to communicate with machines. However, recent research reveals ASR systems are vulnerable to various malicious audio attacks. In particular, by removing…

This paper investigates the real-world vulnerabilities of audio-based large language models (ALLMs), such as Qwen2-Audio. We first demonstrate that an adversary can craft stealthy audio perturbations to manipulate ALLMs into exhibiting…

Quantum computers are hypothetical devices, based on quantum physics, that would enable us to perform certain computations hundreds of orders of magnitude faster than digital computers. This feature is coined as "quantum supremacy" and one…

Currently, Automatic Speech Recognition (ASR) models are deployed in an extensive range of applications. However, recent studies have demonstrated the possibility of adversarial attack on these models which could potentially suppress or…

The growing adoption of electric vehicles, known for their quieter operation compared to internal combustion engine vehicles, raises concerns about their detectability, particularly for vulnerable road users. To address this, regulations…

The advancements in generative AI have enabled the improvement of audio synthesis models, including text-to-speech and voice conversion. This raises concerns about its potential misuse in social manipulation and political interference, as…

Various adversarial audio attacks have recently been developed to fool automatic speech recognition (ASR) systems. We here propose a defense against such attacks based on the uncertainty introduced by dropout in neural networks. We show…

The number of IoT devices in use is increasing rapidly and so is the number of IoT applications. As in any new technology, the rapid development means rapid increase in security threats and attack surfaces. IoT security has proven to be…

Wearable devices, or "wearables," bring great benefits but also potential risks that could expose users' activities with- out their awareness or consent. In this paper, we report findings from the first large-scale survey conducted to…

A vishing attack is a form of social engineering where attackers use phone calls to deceive individuals into disclosing sensitive information, such as personal data, financial information, or security credentials. Attackers exploit the…

Measuring 3D geometric structures of indoor scenes requires dedicated depth sensors, which are not always available. Echo-based depth estimation has recently been studied as a promising alternative solution. All previous studies have…

Privacy and security in Smart Cities remain at constant risk due to the vulnerabilities introduced by Internet of Things (IoT) devices. The limited computational resources of these devices make them especially susceptible to attacks, while…

The increase of cyberattacks using IoT devices has exposed the vulnerabilities in the infrastructures that make up the IoT and have shown how small devices can affect networks and services functioning. This paper presents a review of the…

Machine learning systems based on deep neural networks, being able to produce state-of-the-art results on various perception tasks, have gained mainstream adoption in many applications. However, they are shown to be vulnerable to…

Due to society's continuing technological advance, the capabilities of machine learning-based artificial intelligence systems continue to expand and influence a wider degree of topics. Alongside this expansion of technology, there is a…

High-power microwave applications are growing for both military and civil purposes, yet they can induce brain-related risks and raise important public health concerns. High-power sub-millisecond radio frequency energy pulses have been…

Recent years have seen a surge in the popularity of acoustics-enabled personal devices powered by machine learning. Yet, machine learning has proven to be vulnerable to adversarial examples. A large number of modern systems protect…

Virtual personal assistants (VPA) (e.g., Amazon Alexa and Google Assistant) today mostly rely on the voice channel to communicate with their users, which however is known to be vulnerable, lacking proper authentication. The rapid growth of…

Manufacturers of smart home Internet of Things (IoT) devices are increasingly adding voice assistant and audio monitoring features to a wide range of devices including smart speakers, televisions, thermostats, security systems, and…