Related papers: Light Commands: Laser-Based Audio Injection Attack…
Deepfakes - manipulated or forged audio and video media - pose significant security risks to individuals, organizations, and society at large. To address these challenges, machine learning-based classifiers are commonly employed to detect…
User identification plays a pivotal role in how we interact with our mobile devices. Many existing authentication approaches require active input from the user or specialized sensing hardware, and studies on mobile device usage show…
Recent works have explained the principle of using ultrasonic transmissions to jam nearby microphones. These signals are inaudible to nearby users, but leverage "hardware nonlinearity" to induce a jamming signal inside microphones that…
Voice is envisioned to be a popular way for humans to interact with Internet-of-Things (IoT) devices. We propose a proximity-based user authentication method (called PIANO) for access control on such voice-powered IoT devices. PIANO…
In this paper, we propose PhantomSound, a query-efficient black-box attack toward voice assistants. Existing black-box adversarial attacks on voice assistants either apply substitution models or leverage the intermediate model output to…
Several years of research have shown that machine-learning systems are vulnerable to adversarial examples, both in theory and in practice. Until now, such attacks have primarily targeted visual models, exploiting the gap between human and…
Most electronic devices utilize mechanical keyboards to receive inputs, including sensitive information such as authentication credentials, personal and private data, emails, plans, etc. However, these systems are susceptible to acoustic…
Bluetooth technology has enabled short-range wireless communication for billions of devices. Bluetooth Low-Energy (BLE) variant aims at improving power consumption on battery-constrained devices. BLE-enabled devices broadcast information…
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 models are vulnerable to backdoor attacks, where the adversaries can…
Explicitly alerting users is not always an optimal intervention, especially when they are not motivated to obey. For example, in video-based learning, learners who are distracted from the video would not follow an alert asking them to pay…
In this paper, we present an acoustic side channel attack which makes use of smartphone microphones recording a robot in operation to exploit acoustic properties of the sound to fingerprint a robot's movements. In this work we consider the…
The widespread application of large vision language models has significantly raised safety concerns. In this project, we investigate text prompt injection, a simple yet effective method to mislead these models. We developed an algorithm for…
Since being launched in 2014, Alexa, Amazon's versatile cloud-based voice service, is now active in over 100 million households worldwide. Alexa's user-friendly, personalized vocal experience offers customers a more natural way of…
The emergence of voice-assistant devices ushers in delightful user experiences not just on the smart home front, but also in diverse educational environments from classrooms to personalized-learning/tutoring. However, the use of voice as an…
This paper describes the implementation of a system to recognize employees and visitors wanting to gain access to a physical office through face images and speech-to-text recognition. The system helps employees to unlock the entrance door…
Voice deepfake attacks, which artificially impersonate human speech for malicious purposes, have emerged as a severe threat. Existing defenses typically inject noise into human speech to compromise voice encoders in speech synthesis models.…
Automatic speech recognition and voice identification systems are being deployed in a wide array of applications, from providing control mechanisms to devices lacking traditional interfaces, to the automatic transcription of conversations…
In this paper, we evaluate deep learning-enabled AED systems against evasion attacks based on adversarial examples. We test the robustness of multiple security critical AED tasks, implemented as CNNs classifiers, as well as existing…
Voice Recognition Systems (VRSs) employ deep learning for speech recognition and speaker recognition. They have been widely deployed in various real-world applications, from intelligent voice assistance to telephony surveillance and…
When AI agents retrieve and reason over external documents, adversaries can manipulate the data they receive to subvert their behaviour. Previous research has studied indirect prompt injection, where the attacker injects malicious…