SIA: Smartwatch-Enabled Inference Attacks on Physical Keyboards Using Acoustic Signals. Meteriz-Yıldıran, Ü., Yildiran, N. F., & Mohaisen, D. In Proceedings of the 20th Workshop on Workshop on Privacy in the Electronic Society, of WPES '21, pages 209–221, New York, NY, USA, 2021. Association for Computing Machinery. ![SIA: Smartwatch-Enabled Inference Attacks on Physical Keyboards Using Acoustic Signals [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex The convergence of various technologies, such as smartwatches, smartphones, etc. has proven to be beneficial, although poses various security and privacy risks. In this paper, we explore one such risk where a smartwatch can be exploited to infer what a user is typing on a physical keyboard while wearing the smartwatch. We exploited the acoustic emanations of the keyboard as recorded by the smartwatch to perform the proposed attack-SIA. To address various environment-related challenges, SIA employs four stages: Noise Cancelling, Keystroke Detection, Key Identification, and Word Correction, where several digital signal processing, machine learning, and natural language processing techniques are utilized to produce the final inference. Our results show that an acoustic emanation of a physical keyboard captured by a smartwatch recovers up to 98% of the typed text. We also showed that utilizing the noise cancellation, SIA is robust to the changes in the attack environment, which further boosts the practicality of the attack. The findings are alarming and call for further investigation on methods to cope with inference attacks due to the convergence of those technologies.
@inproceedings{10.1145/3463676.3485607,
author = {Meteriz-Y\i{}ld\i{}ran, \"{U}lk\"{u} and Yildiran, Necip Fazil and Mohaisen, David},
title = {SIA: Smartwatch-Enabled Inference Attacks on Physical Keyboards Using Acoustic Signals},
year = {2021},
isbn = {9781450385275},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3463676.3485607},
doi = {10.1145/3463676.3485607},
abstract = {The convergence of various technologies, such as smartwatches, smartphones, etc. has proven to be beneficial, although poses various security and privacy risks. In this paper, we explore one such risk where a smartwatch can be exploited to infer what a user is typing on a physical keyboard while wearing the smartwatch. We exploited the acoustic emanations of the keyboard as recorded by the smartwatch to perform the proposed attack-SIA. To address various environment-related challenges, SIA employs four stages: Noise Cancelling, Keystroke Detection, Key Identification, and Word Correction, where several digital signal processing, machine learning, and natural language processing techniques are utilized to produce the final inference. Our results show that an acoustic emanation of a physical keyboard captured by a smartwatch recovers up to 98% of the typed text. We also showed that utilizing the noise cancellation, SIA is robust to the changes in the attack environment, which further boosts the practicality of the attack. The findings are alarming and call for further investigation on methods to cope with inference attacks due to the convergence of those technologies.},
booktitle = {Proceedings of the 20th Workshop on Workshop on Privacy in the Electronic Society},
pages = {209–221},
numpages = {13},
keywords = {keylogging, machine learning, natural language processing, noise reduction, signal processing, smartwatch, wearable privacy},
location = {Virtual Event, Republic of Korea},
series = {WPES '21}
}
Downloads: 0
{"_id":"LzQaHSY26ARDqcXav","bibbaseid":"meterizyldran-yildiran-mohaisen-siasmartwatchenabledinferenceattacksonphysicalkeyboardsusingacousticsignals-2021","author_short":["Meteriz-Yıldıran, Ü.","Yildiran, N. F.","Mohaisen, D."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"propositions":[],"lastnames":["Meteriz-Yıldıran"],"firstnames":["Ülkü"],"suffixes":[]},{"propositions":[],"lastnames":["Yildiran"],"firstnames":["Necip","Fazil"],"suffixes":[]},{"propositions":[],"lastnames":["Mohaisen"],"firstnames":["David"],"suffixes":[]}],"title":"SIA: Smartwatch-Enabled Inference Attacks on Physical Keyboards Using Acoustic Signals","year":"2021","isbn":"9781450385275","publisher":"Association for Computing Machinery","address":"New York, NY, USA","url":"https://doi.org/10.1145/3463676.3485607","doi":"10.1145/3463676.3485607","abstract":"The convergence of various technologies, such as smartwatches, smartphones, etc. has proven to be beneficial, although poses various security and privacy risks. In this paper, we explore one such risk where a smartwatch can be exploited to infer what a user is typing on a physical keyboard while wearing the smartwatch. We exploited the acoustic emanations of the keyboard as recorded by the smartwatch to perform the proposed attack-SIA. To address various environment-related challenges, SIA employs four stages: Noise Cancelling, Keystroke Detection, Key Identification, and Word Correction, where several digital signal processing, machine learning, and natural language processing techniques are utilized to produce the final inference. Our results show that an acoustic emanation of a physical keyboard captured by a smartwatch recovers up to 98% of the typed text. We also showed that utilizing the noise cancellation, SIA is robust to the changes in the attack environment, which further boosts the practicality of the attack. The findings are alarming and call for further investigation on methods to cope with inference attacks due to the convergence of those technologies.","booktitle":"Proceedings of the 20th Workshop on Workshop on Privacy in the Electronic Society","pages":"209–221","numpages":"13","keywords":"keylogging, machine learning, natural language processing, noise reduction, signal processing, smartwatch, wearable privacy","location":"Virtual Event, Republic of Korea","series":"WPES '21","bibtex":"@inproceedings{10.1145/3463676.3485607,\nauthor = {Meteriz-Y\\i{}ld\\i{}ran, \\\"{U}lk\\\"{u} and Yildiran, Necip Fazil and Mohaisen, David},\ntitle = {SIA: Smartwatch-Enabled Inference Attacks on Physical Keyboards Using Acoustic Signals},\nyear = {2021},\nisbn = {9781450385275},\npublisher = {Association for Computing Machinery},\naddress = {New York, NY, USA},\nurl = {https://doi.org/10.1145/3463676.3485607},\ndoi = {10.1145/3463676.3485607},\nabstract = {The convergence of various technologies, such as smartwatches, smartphones, etc. has proven to be beneficial, although poses various security and privacy risks. In this paper, we explore one such risk where a smartwatch can be exploited to infer what a user is typing on a physical keyboard while wearing the smartwatch. We exploited the acoustic emanations of the keyboard as recorded by the smartwatch to perform the proposed attack-SIA. To address various environment-related challenges, SIA employs four stages: Noise Cancelling, Keystroke Detection, Key Identification, and Word Correction, where several digital signal processing, machine learning, and natural language processing techniques are utilized to produce the final inference. Our results show that an acoustic emanation of a physical keyboard captured by a smartwatch recovers up to 98% of the typed text. We also showed that utilizing the noise cancellation, SIA is robust to the changes in the attack environment, which further boosts the practicality of the attack. The findings are alarming and call for further investigation on methods to cope with inference attacks due to the convergence of those technologies.},\nbooktitle = {Proceedings of the 20th Workshop on Workshop on Privacy in the Electronic Society},\npages = {209–221},\nnumpages = {13},\nkeywords = {keylogging, machine learning, natural language processing, noise reduction, signal processing, smartwatch, wearable privacy},\nlocation = {Virtual Event, Republic of Korea},\nseries = {WPES '21}\n}\n\n","author_short":["Meteriz-Yıldıran, Ü.","Yildiran, N. F.","Mohaisen, D."],"key":"10.1145/3463676.3485607","id":"10.1145/3463676.3485607","bibbaseid":"meterizyldran-yildiran-mohaisen-siasmartwatchenabledinferenceattacksonphysicalkeyboardsusingacousticsignals-2021","role":"author","urls":{"Paper":"https://doi.org/10.1145/3463676.3485607"},"keyword":["keylogging","machine learning","natural language processing","noise reduction","signal processing","smartwatch","wearable privacy"],"metadata":{"authorlinks":{}},"downloads":0,"html":""},"bibtype":"inproceedings","biburl":"https://bibbase.org/network/files/QDBhwkwh8hDye6xL8","dataSources":["4x87iNQYFcnH8n6Cm"],"keywords":["keylogging","machine learning","natural language processing","noise reduction","signal processing","smartwatch","wearable privacy"],"search_terms":["sia","smartwatch","enabled","inference","attacks","physical","keyboards","using","acoustic","signals","meteriz-yıldıran","yildiran","mohaisen"],"title":"SIA: Smartwatch-Enabled Inference Attacks on Physical Keyboards Using Acoustic Signals","year":2021}