Related papers: Don't Skype & Type! Acoustic Eavesdropping in Voic…
Adversarial perturbations in speech pose a serious threat to automatic speech recognition (ASR) and speaker verification by introducing subtle waveform modifications that remain imperceptible to humans but can significantly alter system…
Secure Device Pairing (SDP) relies on an out-of-band channel to authenticate devices. This requires a common hardware interface, which limits the use of existing SDP systems. We propose to use short-range acoustic communication for the…
Thanks to the popularisation of transformer-based models, speech recognition (SR) is gaining traction in various application fields, such as industrial and robotics environments populated with mission-critical devices. While…
Privacy-preserving voice conversion aims to remove only the attributes of speech audio that convey identity information, keeping other speech characteristics intact. This paper presents a mechanism for privacy-preserving voice conversion…
Large Language Models (LLMs) are increasingly deployed in sensitive domains including healthcare, legal services, and confidential communications, where privacy is paramount. This paper introduces Whisper Leak, a side-channel attack that…
Recent advances in text-to-speech (TTS) systems, particularly those with voice cloning capabilities, have made voice impersonation readily accessible, raising ethical and legal concerns due to potential misuse for malicious activities like…
Adversarial attacks and backdoor attacks are two common security threats that hang over deep learning. Both of them harness task-irrelevant features of data in their implementation. Text style is a feature that is naturally irrelevant to…
While smartphone usage become more and more pervasive, people start also asking to which extent such devices can be maliciously exploited as "tracking devices". The concern is not only related to an adversary taking physical or remote…
Large pre-trained Vision-Language Models (VLMs) such as CLIP have demonstrated excellent zero-shot generalizability across various downstream tasks. However, recent studies have shown that the inference performance of CLIP can be greatly…
The proliferation of smart, connected, always listening devices have introduced significant privacy risks to users in a smart home environment. Beyond the notable risk of eavesdropping, intruders can adopt machine learning techniques to…
The popularity of mobile device has made people's lives more convenient, but threatened people's privacy at the same time. As end users are becoming more and more concerned on the protection of their private information, it is even harder…
Mature push button tools have emerged for checking trace properties (e.g. secrecy or authentication) of security protocols. The case of indistinguishability-based privacy properties (e.g. ballot privacy or anonymity) is more complex and…
Sound-squatting is a phishing attack that tricks users into malicious resources by exploiting similarities in the pronunciation of words. Proactive defense against sound-squatting candidates is complex, and existing solutions rely on…
Quantum key distribution algorithms are considered secure because they leverage quantum phenomena to provide security. As such, eavesdroppers can be detected by analyzing the error rate in the shared key obtained by the parties performing…
Wireless information and power transfer (WIPT) enables more sustainable and resilient communications owing to the fact that it avoids frequent battery charging and replacement. However, it also suffers from possible information interception…
In this paper, we present AltVoice -- a system designed to help user's protect their privacy when using remotely accessed voice services. The system allows a user to conceal their true voice identity information with no cooperation from the…
With the advancements in AI speech synthesis, it is easier than ever before to generate realistic audio in a target voice. One only needs a few seconds of reference audio from the target, quite literally putting words in the target person's…
Due to the open nature of voice input, voice assistant (VA) systems (e.g., Google Home and Amazon Alexa) are under a high risk of sensitive information leakage (e.g., personal schedules and shopping accounts). Though the existing VA systems…
Speech synthesis technology has brought great convenience, while the widespread usage of realistic deepfake audio has triggered hazards. Malicious adversaries may unauthorizedly collect victims' speeches and clone a similar voice for…
Sound at frequencies above (ultrasonic) or below (infrasonic) the range of human hearing can, in some settings, cause adverse physiological and psychological effects to individuals. In this paper, we investigate the feasibility of…