Related papers: Light Commands: Laser-Based Audio Injection Attack…

Voice authentication has undergone significant changes from traditional systems that relied on handcrafted acoustic features to deep learning models that can extract robust speaker embeddings. This advancement has expanded its applications…

In light of the widespread application of Automatic Speech Recognition (ASR) systems, their security concerns have received much more attention than ever before, primarily due to the susceptibility of Deep Neural Networks. Previous studies…

AI assistants are becoming an integral part of society, used for asking advice or help in personal and confidential issues. In this paper, we unveil a novel side-channel that can be used to read encrypted responses from AI Assistants over…

The ability to perform high-precision optical measurements is paramount to science and engineering. Laser interferometry enables interaction-free sensing with a precision ultimately limited by shot noise. Quantum optical sensors can surpass…

As speech translation (ST) systems become increasingly prevalent, understanding their vulnerabilities is crucial for ensuring robust and reliable communication. However, limited work has explored this issue in depth. This paper explores…

Physical isolation, so called air-gapping, is an effective method for protecting security-critical computers and networks. While it might be possible to introduce malicious code through the supply chain, insider attacks, or social…

We introduce a variant of the speaker localization problem, which we call device arbitration. In the device arbitration problem, a user utters a keyword that is detected by multiple distributed microphone arrays (smart home devices), and we…

Previous research about sensor based attacks on Android platform focused mainly on accessing or controlling over sensitive device components, such as camera, microphone and GPS. These approaches get data from sensors directly and need…

We demonstrate how AI-powered cybersecurity tools can be turned against themselves through prompt injection attacks. Prompt injection is reminiscent of cross-site scripting (XSS): malicious text is hidden within seemingly trusted content,…

Safety-oriented instruction-following is supposed to keep LLM-controlled robots safe. We show it also creates an availability attack surface. By injecting short safety-plausible phrases (1-5 tokens) into a robots audio channel, an adversary…

Pattern lock has been widely used for authentication to protect user privacy on mobile devices (e.g., smartphones and tablets). Given its pervasive usage, the compromise of pattern lock could lead to serious consequences. Several attacks…

Recent studies have demonstrated the vulnerability of Automatic Speech Recognition systems to adversarial examples, which can deceive these systems into misinterpreting input speech commands. While previous research has primarily focused on…

Automatic speaker verification (ASV) systems utilize the biometric information in human speech to verify the speaker's identity. The techniques used for performing speaker verification are often vulnerable to malicious attacks that attempt…

Human voices can be used to authenticate the identity of the speaker, but the automatic speaker verification (ASV) systems are vulnerable to voice spoofing attacks, such as impersonation, replay, text-to-speech, and voice conversion.…

Speech recognition systems driven by DNNs have revolutionized human-computer interaction through voice interfaces, which significantly facilitate our daily lives. However, the growing popularity of these systems also raises special concerns…

In a transfer-based attack against Automatic Speech Recognition (ASR) systems, attacks are unable to access the architecture and parameters of the target model. Existing attack methods are mostly investigated in voice assistant scenarios…

Coupling light into microdisk plays a key role in a number of applications such as resonant filters and optical sensors. While several approaches have successfully coupled light into microdisk efficiently, most of them suffer from the…

Model inversion (MI) attacks allow to reconstruct average per-class representations of a machine learning (ML) model's training data. It has been shown that in scenarios where each class corresponds to a different individual, such as face…

Many personal devices have transitioned from visual-controlled interfaces to speech-controlled interfaces to reduce device costs and interactive friction. This transition has been hastened by the increasing capabilities of speech-controlled…

Interactions with virtual assistants typically start with a predefined trigger phrase followed by the user command. To make interactions with the assistant more intuitive, we explore whether it is feasible to drop the requirement that users…