The Hierarchical Hidden Markov Model: Analysis and Applications
Machine Learning
Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition
Advanced Methods in Neural Computing
Advanced Methods in Neural Computing
Artificial Intelligence: A Modern Approach
Artificial Intelligence: A Modern Approach
Optical Time-Domain Eavesdropping Risks of CRT Displays
SP '02 Proceedings of the 2002 IEEE Symposium on Security and Privacy
A second-order Hidden Markov Model for part-of-speech tagging
ACL '99 Proceedings of the 37th annual meeting of the Association for Computational Linguistics on Computational Linguistics
Pass-thoughts: authenticating with our minds
NSPW '05 Proceedings of the 2005 workshop on New security paradigms
Acoustic environment classification
ACM Transactions on Speech and Language Processing (TSLP)
A natural language approach to automated cryptanalysis of two-time pads
Proceedings of the 13th ACM conference on Computer and communications security
Dictionary attacks using keyboard acoustic emanations
Proceedings of the 13th ACM conference on Computer and communications security
Reducing shoulder-surfing by using gaze-based password entry
Proceedings of the 3rd symposium on Usable privacy and security
EATIS '07 Proceedings of the 2007 Euro American conference on Telematics and information systems
Undercover: authentication usable in front of prying eyes
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Defending against sensor-sniffing attacks on mobile phones
Proceedings of the 1st ACM workshop on Networking, systems, and applications for mobile handhelds
TapSongs: tapping rhythm-based passwords on a single binary sensor
Proceedings of the 22nd annual ACM symposium on User interface software and technology
SSSL: shoulder surfing safe login
SoftCOM'09 Proceedings of the 17th international conference on Software, Telecommunications and Computer Networks
Compromising electromagnetic emanations of wired and wireless keyboards
SSYM'09 Proceedings of the 18th conference on USENIX security symposium
Peeping tom in the neighborhood: keystroke eavesdropping on multi-user systems
SSYM'09 Proceedings of the 18th conference on USENIX security symposium
Proceedings of the 17th ACM conference on Computer and communications security
Typing Biometrics: Impact of Human Learning on Performance Quality
Journal of Data and Information Quality (JDIQ)
Acoustic side-channel attacks on printers
USENIX Security'10 Proceedings of the 19th USENIX conference on Security
Crypt analysis of two time pads in case of compressed speech
Computers and Electrical Engineering
(sp)iPhone: decoding vibrations from nearby keyboards using mobile phone accelerometers
Proceedings of the 18th ACM conference on Computer and communications security
ACCessory: password inference using accelerometers on smartphones
Proceedings of the Twelfth Workshop on Mobile Computing Systems & Applications
An emerging threat: eve meets a robot
INTRUST'10 Proceedings of the Second international conference on Trusted Systems
Fingerprint attack against touch-enabled devices
Proceedings of the second ACM workshop on Security and privacy in smartphones and mobile devices
Proceedings of the 7th ACM Symposium on Information, Computer and Communications Security
Exploring mobile proxies for better password authentication
ICICS'12 Proceedings of the 14th international conference on Information and Communications Security
Seeing double: reconstructing obscured typed input from repeated compromising reflections
Proceedings of the 2013 ACM SIGSAC conference on Computer & communications security
Personal identification by flick input with acceleration sensor
Proceedings of the 8th International Conference on Ubiquitous Information Management and Communication
Hi-index | 0.00 |
We examine the problem of keyboard acoustic emanations. We present a novel attack taking as input a 10-minute sound recording of a user typing English text using a keyboard, and then recovering up to 96% of typed characters. There is no need for a labeled training recording. Moreover the recognizer bootstrapped this way can even recognize random text such as passwords: In our experiments, 90% of 5-character random passwords using only letters can be generated in fewer than 20 attempts by an adversary; 80% of 10-character passwords can be generated in fewer than 75 attempts. Our attack uses the statistical constraints of the underlying content, English language, to reconstruct text from sound recordings without any labeled training data. The attack uses a combination of standard machine learning and speech recognition techniques, including cepstrum features, Hidden Markov Models, linear classification, and feedback-based incremental learning.