Related papers: EveGuard: Defeating Vibration-based Side-Channel E…
Neural networks are commonly known to be vulnerable to adversarial attacks mounted through subtle perturbation on the input data. Recent development in voice-privacy protection has shown the positive use cases of the same technique to…
Automatic speaker verification (ASV) systems are highly vulnerable to presentation attacks, also called spoofing attacks. Replay is among the simplest attacks to mount - yet difficult to detect reliably. The generalization failure of…
Virtual reality (VR) has recently proliferated significantly, consisting of headsets or head-mounted displays (HMDs) and hand controllers for an embodied and immersive experience. The VR device is usually embedded with different kinds of…
The research in Environmental Sound Classification (ESC) has been progressively growing with the emergence of deep learning algorithms. However, data scarcity poses a major hurdle for any huge advance in this domain. Data augmentation…
Adversarial audio attacks can be considered as a small perturbation unperceptive to human ears that is intentionally added to the audio signal and causes a machine learning model to make mistakes. This poses a security concern about the…
Voice cloning technology poses significant privacy threats by enabling unauthorized speech synthesis from limited audio samples. Existing defenses based on imperceptible adversarial perturbations are vulnerable to common audio preprocessing…
The widespread smart devices raise people's concerns of being eavesdropped on. To enhance voice privacy, recent studies exploit the nonlinearity in microphone to jam audio recorders with inaudible ultrasound. However, existing solutions…
Adversarial evasion attacks have been very successful in causing poor performance in a wide variety of machine learning applications. One such application is radio frequency spectrum sensing. While evasion attacks have proven particularly…
Classical parametric speech coding techniques provide a compact representation for speech signals. This affords a very low transmission rate but with a reduced perceptual quality of the reconstructed signals. Recently, autoregressive deep…
Malicious applications of visual manipulation have raised serious threats to the security and reputation of users in many fields. To alleviate these issues, adversarial noise-based defenses have been enthusiastically studied in recent…
Adversarial attacks aim to disturb the functionality of a target system by adding specific noise to the input samples, bringing potential threats to security and robustness when applied to facial recognition systems. Although existing…
Advances in automatic speaker verification (ASV) promote research into the formulation of spoofing detection systems for real-world applications. The performance of ASV systems can be degraded severely by multiple types of spoofing attacks,…
Our voice encodes a uniquely identifiable pattern which can be used to infer private attributes, such as gender or identity, that an individual might wish not to reveal when using a speech recognition service. To prevent attribute inference…
Embeddings have become a cornerstone in the functionality of large language models (LLMs) due to their ability to transform text data into rich, dense numerical representations that capture semantic and syntactic properties. These embedding…
Audio watermarking has been widely applied in copyright protection and source tracing. However, due to the inherent characteristics of audio signals, watermark localization and resistance to desynchronization attacks remain significant…
Previous works have shown that automatic speaker verification (ASV) is seriously vulnerable to malicious spoofing attacks, such as replay, synthetic speech, and recently emerged adversarial attacks. Great efforts have been dedicated to…
Voice anonymization has been developed as a technique for preserving privacy by replacing the speaker's voice in a speech signal with that of a pseudo-speaker, thereby obscuring the original voice attributes from machine recognition and…
Closed-weight generative services are increasingly deployed through query-based APIs, where users can obtain generated outputs while model parameters remain inaccessible. However, such deployment does not prevent model stealing: an attacker…
The high directionality of millimeter-wave (mmWave) communication systems has proven effective in reducing the attack surface against eavesdropping, thus improving the physical layer security. However, even with highly directional beams,…
Recent advancements in large audio-language models (LALMs) have enabled speech-based user interactions, significantly enhancing user experience and accelerating the deployment of LALMs in real-world applications. However, ensuring the…