Defending against Thru-barrier Stealthy Voice Attacks via Cross-Domain Sensing on Phoneme Sounds
2022 IEEE 42nd International Conference on Distributed Computing Systems (ICDCS)(2022)
摘要
The open nature of voice input makes voice assistant (VA) systems vulnerable to various acoustic attacks (e.g., replay and voice synthesis attacks). A simple yet effective way for adversaries to launch these attacks is to hide behind barriers (e.g., a wall, a window, or a door) and give unauthorized voice commands without being observed by legitimate users. In this work, we develop an automated, training-free defense system that can protect VA systems from such thru-barrier acoustic attacks. Our study finds that acoustic signals passing through the barriers generally present a unique frequency-selective effect in the vibration domain. Thus, we propose to devise a system to capture this unique effect of barriers by leveraging low-cost, cross-domain sensing available in users’ wearables. The system replays the audio-domain signals with the wearable’s speaker and captures the conductive vibrations caused by the audio sounds in the vibration domain via the built-in accelerometer. To improve the proposed system’s reliability, we develop a unique vibration-domain enhancement method to extract the phonemes most sensitive to the frequency-selective effect of barriers. We identify effective vibration-domain features that capture the barriers’ effects in the vibration domain. A 2D-correlation-based method is developed to examine the speech similarity between the recordings from the VA system and the user’s wearable and detect thru-barrier attacks. Extensive experiments with various barriers and environments demonstrate that the proposed defense system can effectively defend random, replay, synthesis, and hidden voice attacks with less than 4% equal error rates.
更多查看译文
关键词
unique vibration-domain enhancement method,effective vibration-domain features,barriers,vibration domain,VA system,thru-barrier attacks,replay,hidden voice attacks,thru-barrier stealthy voice attacks,cross-domain sensing,phoneme sounds,voice input,voice assistant systems,voice synthesis attacks,simple yet effective way,unauthorized voice commands,automated training-free defense system,thru-barrier acoustic attacks,acoustic signals,unique frequency-selective effect,unique effect,users,audio-domain signals,conductive vibrations,audio sounds
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要