MagBackdoor: Beware of Your Loudspeaker as A Backdoor For Magnetic Injection Attacks
Tiantian Liu, Feng Lin, Zhangsen Wang, Chao Wang, Zhongjie Ba, Li Lu, Wenyao Xu, Kui Ren
摘要
An audio system containing loudspeakers and microphones is the fundamental hardware for voice-enabled devices, enabling voice interaction with mobile applications and smart homes. This paper presents MagBackdoor, the first magnetic field attack that injects malicious commands via a loudspeaker-based backdoor of the audio system, compromising the linked voice interaction system. MagBackdoor focuses on the magnetic threat on loudspeakers and manipulates their sound production stealthily. Consequently, the microphone will inevitably pick up malicious sound generated by the attacked speaker, due to the closely packed arrangement of internal audio systems. To prove the feasibility of MagBackdoor, we conduct comprehensive simulations and experiments. This study further models the mechanism by which an external magnetic field excites the sound production of loudspeakers, giving theoretical guidance to MagBackdoor. Aiming at stealthy magnetic attacks in real-world scenarios, we self-design a prototype that can emit magnetic fields modulated by voice commands. We implement MagBackdoor and evaluate it across a wide range of smart devices involving 16 smartphones, four laptops, two tablets, and three smart speakers, achieving an average 95% injection success rate with high-quality injected acoustic signals.
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 Paper5
- WavoID: Robust and Secure Multi-modal User Identification via mmWave-voice MechanismTiantian Liu, Feng Lin, Chao Wang, Chenhan Xu 等UIST 2023 · 被引用 19 次
- XPorter: A Study of the Multi-Port Charger Security on Privacy Leakage and Voice InjectionTao Ni, Yongliang Chen, Weitao Xu, Lei Xue 等MobiCom 2023 · 被引用 15 次
- MicGuard: A Comprehensive Detection System against Out-of-band Injection Attacks for Different Level Microphone-based DevicesTiantian Liu, Feng Lin, Zhongjie Ba, Li Lu 等USENIX Security 2024 · 被引用 4 次
- SoK: Security of Cyber-physical Systems Under Intentional Electromagnetic Interference AttacksQinhong Jiang, Yan Long, Youqian Zhang, Chen Yan 等USENIX Security 2026
- PhantomLiDAR: Cross-modality Signal Injection Attacks against LiDARZizhi Jin, Qinhong Jiang, Xuancun Lu, Chen Yan 等NDSS 2025
它引用的顶会 Paper9
- 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
- Adversarial Attacks Against Automatic Speech Recognition Systems via Psychoacoustic HidingLea Schönherr, Katharina Kohls, Steffen Zeiler, Thorsten Holz 等NDSS 2019 · 被引用 315 次
- Practical Hidden Voice Attacks against Speech and Speaker Recognition SystemsHadi Abdullah, Washington Garcia, Christian Peeters, Patrick Traynor 等NDSS 2019 · 被引用 180 次
相关 Paper
- Devil in the Room: Triggering Audio Backdoors in the Physical WorldMeng Chen, Xiangyu Xu, Li Lu, Zhongjie Ba 等USENIX Security 2024 · 被引用 7 次
- Inducing Wireless Chargers to Voice Out for Inaudible Command AttacksDonghui Dai, Zhenlin An, Lei YangS&P 2023
- CapSpeaker: Injecting Voices to Microphones via CapacitorsXiaoyu Ji, Juchuan Zhang, Shui Jiang, Jishen Li 等CCS 2021 · 被引用 21 次
- Audio-domain position-independent backdoor attack via unnoticeable triggersCong Shi, Tianfang Zhang, Zhuohang Li, Huy Phan 等MobiCom 2022 · 被引用 54 次
- MASTERKEY: Practical Backdoor Attack Against Speaker Verification SystemsHanqing Guo, Xun Chen, Junfeng Guo, Li Xiao 等MobiCom 2023 · 被引用 14 次
