TY - GEN
T1 - WritingHacker
T2 - 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing, UbiComp 2016
AU - Yu, Tuo
AU - Jin, Haiming
AU - Nahrstedt, Klara
N1 - Funding Information:
This research was funded by the National Science Foundation under award number CNS-1330491. The views and conclusions contained in this document are those of the authors and should not be interpreted as necessarily representing the official policies, either expressed or implied, of the sponsors.
Publisher Copyright:
© 2016 ACM.
PY - 2016/9/12
Y1 - 2016/9/12
N2 - When filling out privacy-related forms in public places such as hospitals or clinics, people usually are not aware that the sound of their handwriting leaks personal information. In this paper, we explore the possibility of eavesdropping on handwriting via nearby mobile devices based on audio signal processing and machine learning. By presenting a proof-ofconcept system, WritingHacker, we show the usage of mobile devices to collect the sound of victims' handwriting, and to extract handwriting-specific features for machine learning based analysis. WritingHacker focuses on the situation where the victim's handwriting follows certain print style. An attacker can keep a mobile device, such as a common smartphone, touching the desk used by the victim to record the audio signals of handwriting. Then the system can provide a word-level estimate for the content of the handwriting. To reduce the impacts of various writing habits and writing locations, the system utilizes the methods of letter clustering and dictionary filtering. Our prototype system's experimental results show that the accuracy of word recognition reaches around 50% - 60% under certain conditions, which reveals the danger of privacy leakage through the sound of handwriting.
AB - When filling out privacy-related forms in public places such as hospitals or clinics, people usually are not aware that the sound of their handwriting leaks personal information. In this paper, we explore the possibility of eavesdropping on handwriting via nearby mobile devices based on audio signal processing and machine learning. By presenting a proof-ofconcept system, WritingHacker, we show the usage of mobile devices to collect the sound of victims' handwriting, and to extract handwriting-specific features for machine learning based analysis. WritingHacker focuses on the situation where the victim's handwriting follows certain print style. An attacker can keep a mobile device, such as a common smartphone, touching the desk used by the victim to record the audio signals of handwriting. Then the system can provide a word-level estimate for the content of the handwriting. To reduce the impacts of various writing habits and writing locations, the system utilizes the methods of letter clustering and dictionary filtering. Our prototype system's experimental results show that the accuracy of word recognition reaches around 50% - 60% under certain conditions, which reveals the danger of privacy leakage through the sound of handwriting.
KW - Audio signals
KW - Eavesdropping
KW - Handwriting
UR - http://www.scopus.com/inward/record.url?scp=84991474874&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84991474874&partnerID=8YFLogxK
U2 - 10.1145/2971648.2971681
DO - 10.1145/2971648.2971681
M3 - Conference contribution
AN - SCOPUS:84991474874
T3 - UbiComp 2016 - Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing
SP - 463
EP - 473
BT - UbiComp 2016 - Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing
PB - Association for Computing Machinery, Inc
Y2 - 12 September 2016 through 16 September 2016
ER -