Audio Hotspot Attack: An Attack on Voice Assistance Systems Using Directional Sound Beams and its Feasibility

被引:11
作者
Iijima, Ryo [1 ,2 ]
Minami, Shota [1 ]
Zhou, Yunao [1 ]
Takehisa, Tatsuya [2 ]
Takahashi, Takeshi [2 ]
Oikawa, Yasuhiro [1 ]
Mori, Tatsuya [1 ,2 ,3 ]
机构
[1] Waseda Univ, Shinjuku City, Tokyo 1698050, Japan
[2] Natl Inst Informat & Commun Technol, Koganei, Tokyo 1840015, Japan
[3] RIKEN AIP, Chuo City, Tokyo 1030027, Japan
关键词
Loudspeakers; Ultrasonic imaging; Acoustic beams; Frequency modulation; Amplitude modulation; Acoustics; Speech recognition; Voice assistance systems; voice commands attack; ultrasonic; security; acoustics; Internet of Things;
D O I
10.1109/TETC.2019.2953041
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
We propose a novel attack, called an "Audio Hotspot Attack," which performs an inaudible malicious voice command attack, by targeting voice assistance systems, e.g., smart speakers or in-car navigation systems. The key idea of the approach is to leverage directional sound beams generated from parametric loudspeakers, which emit amplitude-modulated ultrasounds that will be self-demodulated in the air. Our work goes beyond the previous studies of inaudible voice command attack in the following three aspects: (1) the attack can succeed on a long distance (3.5 meters in a small room, and 12 meters in a long hallway), (2) it can control the spot of the audible area by using two directional sound beams, which consist of a carrier wave and a sideband wave, and (3) the proposed attack leverages a physical phenomenon i.e., non-linearity in the air, to attack voice assistance systems. To evaluate the feasibility of the attack, we performed extensive in-lab experiments and a user study involving 20 participants. The results demonstrated that the attack was feasible in a real-world setting. We discussed the extent of the threat, as well as the possible countermeasures against the attack.
引用
收藏
页码:2004 / 2018
页数:15
相关论文
共 41 条
  • [1] Accuphase, 2001, AC
  • [2] Amazon, 2018, AM POLL
  • [3] Amazon[US], 2018, AM AL
  • [4] [Anonymous], 2017, 30107 ISOIEC
  • [5] [Anonymous], 1994, Matlab
  • [6] Apple, 2018, IOS SIR
  • [7] B&K, 2018, PROD DAT TEDS MICR B
  • [8] Audio Adversarial Examples: Targeted Attacks on Speech-to-Text
    Carlini, Nicholas
    Wagner, David
    [J]. 2018 IEEE SYMPOSIUM ON SECURITY AND PRIVACY WORKSHOPS (SPW 2018), 2018, : 1 - 7
  • [9] Carlini N, 2016, PROCEEDINGS OF THE 25TH USENIX SECURITY SYMPOSIUM, P513
  • [10] Center for Hearing and Communication, 2018, COMM ENV NOIS LEV