AuthGlass: Enhancing Voice Authentication on Smart Glasses via Air-Bone Acoustic Features

2025-09-25

AI Summary

Voice authentication for smart glasses is vulnerable to replay/synthetic spoofing attacks and environmental noise, exhibiting insufficient robustness. To address this, we propose the first air-conduction (AC) and bone-conduction (BC) dual-modal voice authentication method tailored for smart glasses. We design a prototype system integrating 14 AC microphones and 2 BC sensors to form a redundant, synchronized acoustic sensing array. We further introduce a fusion modeling algorithm that jointly encodes spatial sound-field features and craniofacial vibration dynamics, simultaneously enhancing liveness discrimination and noise robustness. Evaluated in multi-scenario experiments involving 42 participants, our method achieves 98.7% authentication accuracy—outperforming single-modal baselines by +12.4%—and maintains stable performance under realistic adversarial conditions, including high ambient noise and replay attacks. This work pioneers on-glasses dual-path acoustic协同 perception, establishing a new paradigm for secure voice interaction on wearable devices.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Multi-modal Vision
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Security and Privacy: Large-scale security measurements
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search

Abstract

With the rapid advancement of smart glasses, voice interaction has become widely deployed due to its naturalness and convenience. However, its practicality is often undermined by the vulnerability to spoofing attacks and interference from surrounding sounds, making seamless voice authentication crucial for smart glasses usage. To address this challenge, we propose AuthGlass, a voice authentication approach that leverages both air- and bone-conducted speech features to enhance accuracy and liveness detection. Aiming to gain comprehensive knowledge on speech-related acoustic and vibration features, we built a smart glasses prototype with redundant synchronized microphones: 14 air-conductive microphones and 2 bone-conductive units. In a study with 42 participants, we validated that combining sound-field and vibration features significantly improves authentication robustness and attack resistance. Furthermore, experiments demonstrated that AuthGlass maintains competitive accuracy even under various practical scenarios, highlighting its applicability and scalability for real-world deployment.

Problem

• Addressing voice authentication vulnerability to spoofing attacks on smart glasses
• Overcoming interference from surrounding sounds during voice authentication processes
• Enhancing liveness detection accuracy for secure voice interaction on wearables

Innovation

• Leveraging air-bone acoustic features for authentication
• Using 14 air and 2 bone microphones synchronized
• Combining sound-field vibration features improves security