Near-Ultrasound Inaudible Trojan (Nuit): Exploiting Your Speaker to Attack Your Microphone
Qi Xia, Qian Chen, Shouhuai Xu
摘要
Voice Control Systems (VCSs) offer a convenient interface for issuing voice commands to smart devices. However, VCS security has yet to be adequately understood and addressed as evidenced by the presence of two classes of attacks: (i) inaudible attacks, which can be waged when the attacker and the victim are in proximity to each other; and (ii) audible attacks, which can be waged remotely by embedding attack signals into audios. In this paper, we introduce a new class of attacks, dubbed near-ultrasound inaudible trojan (NUIT). NUIT attacks achieve the best of the two classes of attacks mentioned above: they are inaudible and can be waged remotely. Moreover, NUIT attacks can achieve end-to-end unnoticeability, which is important but has not been paid due attention in the literature. Another feature of NUIT attacks is that they exploit victim speakers to attack victim microphones and their associated VCSs, meaning the attacker does not need to use any special speaker. We demonstrate the feasibility of NUIT attacks and propose an effective defense against them. Whisper [19] Cable length < 6k No Yes NUIT (This work) Remote 16k-22k No No Attacker embeds audible but human-incomprehensible attack signals into audible base audios (e.g. music) CommanderSong [6] Remote <16k No No Metaphor [7] Remote <6k No No Attacker exploits audible but human-incomprehensible attack signals without using any carrier audios CocainNoodle [20] Remote <6k No No Hidden Voice [21] Remote <6k No No
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper3
- Sirens' Whisper: Inaudible Near-Ultrasonic Jailbreaks of Speech-Driven LLMsZijian Ling, Pingyi Hu, Xiuyong Gao, Xiaojing Ma 等USENIX Security 2026 · 被引用 185 次
- SoK: Understanding the Fundamentals and Implications of Sensor Out-of-band VulnerabilitiesShilin Xiao, Wenjun Zhu, Yan Jiang, Kai Wang 等NDSS 2026 · 被引用 3 次
- Hearing Without Noticing? Attention-Aware Stealthy Black-Box Adversarial Audio AttacksTianyi Xu, Cheng'an Wei, Yue Zhao, Kai ChenICML 2026
它引用的顶会 Paper11
- DolphinAttack: Inaudible Voice CommandsGuoming Zhang, Chen Yan, Xiaoyu Ji, Tianchen Zhang 等CCS 2017 · 被引用 753 次
- Hidden Voice CommandsNicholas Carlini, Pratyush Mishra, Tavish Vaidya, Yuankai Zhang 等USENIX Security 2016 · 被引用 672 次
- CommanderSong: A Systematic Approach for Practical Adversarial Voice RecognitionXuejing Yuan, Yuxuan Chen, Yue Zhao, Yunhui Long 等USENIX Security 2018 · 被引用 389 次
- Using Sonar for Liveness Detection to Protect Smart Speakers against Remote AttackersYeonjoon Lee, Yue Zhao, Jiutian Zeng, Kwangwuk Lee 等UbiComp 2020 · 被引用 36 次
- CapSpeaker: Injecting Voices to Microphones via CapacitorsXiaoyu Ji, Juchuan Zhang, Shui Jiang, Jishen Li 等CCS 2021 · 被引用 21 次
相关 Paper
- Light Commands: Laser-Based Audio Injection Attacks on Voice-Controllable SystemsTakeshi Sugawara, Benjamin Cyr, Sara Rampazzi, Daniel Genkin 等USENIX Security 2020
- Inducing Wireless Chargers to Voice Out for Inaudible Command AttacksDonghui Dai, Zhenlin An, Lei YangS&P 2023
- EarArray: Defending against DolphinAttack via Acoustic AttenuationGuoming Zhang, Xiaoyu Ji, Xinfeng Li, Gang Qu 等NDSS 2021
- Learning Normality is Enough: A Software-based Mitigation against Inaudible Voice AttacksXinfeng Li, Xiaoyu Ji, Chen Yan, Chaohao Li 等USENIX Security 2023
- SurfingAttack: Interactive Hidden Attack on Voice Assistants Using Ultrasonic Guided WavesQiben Yan, Kehai Liu, Qin Zhou, Hanqing Guo 等NDSS 2020
