Fingerprinting Smartphones Based on Microphone Characteristics From Environment Affected Recordings
Fingerprinting devices based on unique characteristics of their sensors is an important research direction nowadays due to its immediate impact on non-interactive authentications and no less due to privacy implications. In this work, we investigate smartphone fingerprints obtained from microphone da...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9955522/ |
| _version_ | 1811322171774992384 |
|---|---|
| author | Adriana Berdich Bogdan Groza Efrat Levy Asaf Shabtai Yuval Elovici Rene Mayrhofer |
| author_facet | Adriana Berdich Bogdan Groza Efrat Levy Asaf Shabtai Yuval Elovici Rene Mayrhofer |
| author_sort | Adriana Berdich |
| collection | DOAJ |
| description | Fingerprinting devices based on unique characteristics of their sensors is an important research direction nowadays due to its immediate impact on non-interactive authentications and no less due to privacy implications. In this work, we investigate smartphone fingerprints obtained from microphone data based on recordings containing human speech, environmental sounds and several live recordings performed outdoors. We record a total of 19,200 samples using distinct devices as well as identical microphones placed on the same device in order to check the limits of the approach. To comply with real-world circumstances, we also consider the presence of several types of noise that is specific to the scenarios which we address, e.g., traffic and market noise at distinct volumes, and may reduce the reliability of the data. We analyze several classification techniques based on traditional machine learning algorithms and more advanced deep learning architectures that are put to test in recognizing devices from the recordings they made. The results indicate that the classical Linear Discriminant classifier and a deep-learning Convolutional Neural Network have comparable success rates while outperforming all the rest of the classifiers. |
| first_indexed | 2024-04-13T13:30:34Z |
| format | Article |
| id | doaj.art-89ac47534d0d43988c0baf987ace0351 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-13T13:30:34Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-89ac47534d0d43988c0baf987ace03512022-12-22T02:44:59ZengIEEEIEEE Access2169-35362022-01-011012239912241310.1109/ACCESS.2022.32233759955522Fingerprinting Smartphones Based on Microphone Characteristics From Environment Affected RecordingsAdriana Berdich0https://orcid.org/0000-0002-7646-7825Bogdan Groza1https://orcid.org/0000-0003-3078-3635Efrat Levy2https://orcid.org/0000-0001-9156-0254Asaf Shabtai3https://orcid.org/0000-0003-0630-4059Yuval Elovici4https://orcid.org/0000-0002-9641-128XRene Mayrhofer5https://orcid.org/0000-0003-1566-4646Faculty of Automatics and Computers, Politehnica University of Timisoara, Timişoara, Timiş, RomaniaFaculty of Automatics and Computers, Politehnica University of Timisoara, Timişoara, Timiş, RomaniaFaculty of Information Systems Engineering, Ben-Gurion University of the Negev, Be’er-Sheva, IsraelFaculty of Information Systems Engineering, Ben-Gurion University of the Negev, Be’er-Sheva, IsraelFaculty of Information Systems Engineering, Ben-Gurion University of the Negev, Be’er-Sheva, IsraelLIT Secure and Correct Systems Laboratory, Institute of Networks and Security, Johannes Kepler University Linz, Linz, AustriaFingerprinting devices based on unique characteristics of their sensors is an important research direction nowadays due to its immediate impact on non-interactive authentications and no less due to privacy implications. In this work, we investigate smartphone fingerprints obtained from microphone data based on recordings containing human speech, environmental sounds and several live recordings performed outdoors. We record a total of 19,200 samples using distinct devices as well as identical microphones placed on the same device in order to check the limits of the approach. To comply with real-world circumstances, we also consider the presence of several types of noise that is specific to the scenarios which we address, e.g., traffic and market noise at distinct volumes, and may reduce the reliability of the data. We analyze several classification techniques based on traditional machine learning algorithms and more advanced deep learning architectures that are put to test in recognizing devices from the recordings they made. The results indicate that the classical Linear Discriminant classifier and a deep-learning Convolutional Neural Network have comparable success rates while outperforming all the rest of the classifiers.https://ieeexplore.ieee.org/document/9955522/Machine learningmicrophonesmartphone fingerprinting |
| spellingShingle | Adriana Berdich Bogdan Groza Efrat Levy Asaf Shabtai Yuval Elovici Rene Mayrhofer Fingerprinting Smartphones Based on Microphone Characteristics From Environment Affected Recordings IEEE Access Machine learning microphone smartphone fingerprinting |
| title | Fingerprinting Smartphones Based on Microphone Characteristics From Environment Affected Recordings |
| title_full | Fingerprinting Smartphones Based on Microphone Characteristics From Environment Affected Recordings |
| title_fullStr | Fingerprinting Smartphones Based on Microphone Characteristics From Environment Affected Recordings |
| title_full_unstemmed | Fingerprinting Smartphones Based on Microphone Characteristics From Environment Affected Recordings |
| title_short | Fingerprinting Smartphones Based on Microphone Characteristics From Environment Affected Recordings |
| title_sort | fingerprinting smartphones based on microphone characteristics from environment affected recordings |
| topic | Machine learning microphone smartphone fingerprinting |
| url | https://ieeexplore.ieee.org/document/9955522/ |
| work_keys_str_mv | AT adrianaberdich fingerprintingsmartphonesbasedonmicrophonecharacteristicsfromenvironmentaffectedrecordings AT bogdangroza fingerprintingsmartphonesbasedonmicrophonecharacteristicsfromenvironmentaffectedrecordings AT efratlevy fingerprintingsmartphonesbasedonmicrophonecharacteristicsfromenvironmentaffectedrecordings AT asafshabtai fingerprintingsmartphonesbasedonmicrophonecharacteristicsfromenvironmentaffectedrecordings AT yuvalelovici fingerprintingsmartphonesbasedonmicrophonecharacteristicsfromenvironmentaffectedrecordings AT renemayrhofer fingerprintingsmartphonesbasedonmicrophonecharacteristicsfromenvironmentaffectedrecordings |