Protecting Voice-Controlled Devices against LASER Injection Attacks

被引：1

作者：

Ali, Hashim ^{[1
]}

Khuttan, Dhimant ^{[1
]}

Refat, Rafi Ud Daula ^{[1
]}

Malik, Hafiz ^{[1
]}

机构：

[1] Univ Michigan Dearborn, Dept Elect Engn, Dearborn, MI 48128 USA

来源：

2023 IEEE INTERNATIONAL WORKSHOP ON INFORMATION FORENSICS AND SECURITY, WIFS | 2023年

关键词：

Audio Forensics; Content Authenticity; Machine Learning;

D O I：

10.1109/WIFS58808.2023.10374658

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Voice-Controllable Devices (VCDs) have seen an increasing trend towards their adoption due to the small form factor of the MEMS microphones and their easy integration into modern gadgets. Recent studies have revealed that MEMS microphones are vulnerable to audio-modulated laser injection attacks. This paper aims to develop countermeasures to detect and prevent laser injection attacks on MEMS microphones. A time-frequency decomposition based on discrete wavelet transform (DWT) is employed to decompose microphone output audio signal into n + 1 frequency subbands to capture photo-acoustic related artifacts. Higher-order statistical features consisting of the first four moments of subband audio signals, e.g., variance, skew, and kurtosis are used to distinguish between acoustic and photo-acoustic responses. An SVM classifier is used to learn the underlying model that differentiates between an acousticand laser-induced (photo-acoustic) response in the MEMS microphone. The proposed framework is evaluated on a data set of 190 audios, consisting of 19 speakers. The experimental results indicate that the proposed framework is able to correctly classify 98% of the acoustic- and laser-induced audio in a random data partition setting and 100% of the audio in speaker-independent and text-independent data partition settings.

引用

页数：6

共 29 条

[1]

Abidi ME, 2018, PROCEEDINGS OF THE 2018 7TH INTERNATIONAL CONFERENCE ON COMPUTER AND COMMUNICATION ENGINEERING (ICCCE), P246, DOI 10.1109/ICCCE.2018.8539258

[2] Replay spoofing countermeasure using autoencoder and siamese networks on ASVspoof 2019 challenge [J].

Adiban, Mohammad ;

Sameti, Hossein ;

Shehnepoor, Saeedreza .

COMPUTER SPEECH AND LANGUAGE, 2020, 64

[3]

amazon, Amazon Alexa Voice AI-Alexa Developer Official Site-developer.amazon.com

[4] Toward Robust Audio Spoofing Detection: A Detailed Comparison of Traditional and Learned Features [J].

Balamurali, B. T. ;

Lin, Kin Wan Edward ;

Lui, Simon ;

Chen, Jer-Ming ;

Herremans, Dorien .

IEEE ACCESS, 2019, 7 :84229-84241

[5] Recent developments in MEMS sensors: a review of applications, markets and technologies [J].

Bogue, Robert .

SENSOR REVIEW, 2013, 33 (04) :300-304

[6]

Cai WC, 2019, Arxiv, DOI arXiv:1907.02663

[7]

Chen NX, 2015, 16TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2015), VOLS 1-5, P2097

[8] ResNet and Model Fusion for Automatic Spoofing Detection [J].

Chen, Zhuxin ;

Xie, Zhifeng ;

Zhang, Weibin ;

Xu, Xiangmin .

18TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2017), VOLS 1-6: SITUATED INTERACTION, 2017, :102-106

[9] Why Lasers Inject Perceived Sound Into MEMS Microphones: Indications and Contraindications of Photoacoustic and Photoelectric Effects [J].

Cyr, Benjamin ;

Sugawara, Takeshi ;

Fu, Kevin .

2021 IEEE SENSORS, 2021,

[10]

Das RK, 2019, 2019 IEEE AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING WORKSHOP (ASRU 2019), P1018, DOI [10.1109/asru46091.2019.9003845, 10.1109/ASRU46091.2019.9003845]

← 1 2 3 →