Noise tolerant symbolic learning of Markov models of tunneled protocols

Harakrishnan Bhanu, Jason Schwier, Ryan Craven, Ilker Ozcelik, Christopher Griffin, Richard R. Brooks

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Recent research has exposed timing side channel vulnerabilities in many security applications. Hidden Markov models (HMMs) have used timing data to extract passwords from cryptographically protected communications tunnels. We extend that work to show how HMM models of protocols can be extracted directly from observations of protocol timing artifacts with no a priori knowledge. Since our approach uses symbolic reasoning, an important question is how to best translate continuous data observations to symbolic data. This translation is problematic when observation variance makes continuous to symbolic translation unreliable. We examine this problem and show that the HMMs we infer compensate automatically for significant observation jitter and symbol misclassification. Experimental verification is presented.

Original languageEnglish (US)
Title of host publicationIWCMC 2011 - 7th International Wireless Communications and Mobile Computing Conference
Pages1310-1314
Number of pages5
DOIs
StatePublished - Sep 12 2011
Event7th International Wireless Communications and Mobile Computing Conference, IWCMC 2011 - Istanbul, Turkey
Duration: Jul 4 2011Jul 8 2011

Publication series

NameIWCMC 2011 - 7th International Wireless Communications and Mobile Computing Conference

Conference

Conference7th International Wireless Communications and Mobile Computing Conference, IWCMC 2011
CountryTurkey
CityIstanbul
Period7/4/117/8/11

Fingerprint

Hidden Markov models
Network protocols
learning
Jitter
Tunnels
symbol
artifact
communications
vulnerability
Communication
knowledge

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Communication

Cite this

Bhanu, H., Schwier, J., Craven, R., Ozcelik, I., Griffin, C., & Brooks, R. R. (2011). Noise tolerant symbolic learning of Markov models of tunneled protocols. In IWCMC 2011 - 7th International Wireless Communications and Mobile Computing Conference (pp. 1310-1314). [5982729] (IWCMC 2011 - 7th International Wireless Communications and Mobile Computing Conference). https://doi.org/10.1109/IWCMC.2011.5982729
Bhanu, Harakrishnan ; Schwier, Jason ; Craven, Ryan ; Ozcelik, Ilker ; Griffin, Christopher ; Brooks, Richard R. / Noise tolerant symbolic learning of Markov models of tunneled protocols. IWCMC 2011 - 7th International Wireless Communications and Mobile Computing Conference. 2011. pp. 1310-1314 (IWCMC 2011 - 7th International Wireless Communications and Mobile Computing Conference).
@inproceedings{3399eabbc818409b8e3d845d72641259,
title = "Noise tolerant symbolic learning of Markov models of tunneled protocols",
abstract = "Recent research has exposed timing side channel vulnerabilities in many security applications. Hidden Markov models (HMMs) have used timing data to extract passwords from cryptographically protected communications tunnels. We extend that work to show how HMM models of protocols can be extracted directly from observations of protocol timing artifacts with no a priori knowledge. Since our approach uses symbolic reasoning, an important question is how to best translate continuous data observations to symbolic data. This translation is problematic when observation variance makes continuous to symbolic translation unreliable. We examine this problem and show that the HMMs we infer compensate automatically for significant observation jitter and symbol misclassification. Experimental verification is presented.",
author = "Harakrishnan Bhanu and Jason Schwier and Ryan Craven and Ilker Ozcelik and Christopher Griffin and Brooks, {Richard R.}",
year = "2011",
month = "9",
day = "12",
doi = "10.1109/IWCMC.2011.5982729",
language = "English (US)",
isbn = "9781424495399",
series = "IWCMC 2011 - 7th International Wireless Communications and Mobile Computing Conference",
pages = "1310--1314",
booktitle = "IWCMC 2011 - 7th International Wireless Communications and Mobile Computing Conference",

}

Bhanu, H, Schwier, J, Craven, R, Ozcelik, I, Griffin, C & Brooks, RR 2011, Noise tolerant symbolic learning of Markov models of tunneled protocols. in IWCMC 2011 - 7th International Wireless Communications and Mobile Computing Conference., 5982729, IWCMC 2011 - 7th International Wireless Communications and Mobile Computing Conference, pp. 1310-1314, 7th International Wireless Communications and Mobile Computing Conference, IWCMC 2011, Istanbul, Turkey, 7/4/11. https://doi.org/10.1109/IWCMC.2011.5982729

Noise tolerant symbolic learning of Markov models of tunneled protocols. / Bhanu, Harakrishnan; Schwier, Jason; Craven, Ryan; Ozcelik, Ilker; Griffin, Christopher; Brooks, Richard R.

IWCMC 2011 - 7th International Wireless Communications and Mobile Computing Conference. 2011. p. 1310-1314 5982729 (IWCMC 2011 - 7th International Wireless Communications and Mobile Computing Conference).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Noise tolerant symbolic learning of Markov models of tunneled protocols

AU - Bhanu, Harakrishnan

AU - Schwier, Jason

AU - Craven, Ryan

AU - Ozcelik, Ilker

AU - Griffin, Christopher

AU - Brooks, Richard R.

PY - 2011/9/12

Y1 - 2011/9/12

N2 - Recent research has exposed timing side channel vulnerabilities in many security applications. Hidden Markov models (HMMs) have used timing data to extract passwords from cryptographically protected communications tunnels. We extend that work to show how HMM models of protocols can be extracted directly from observations of protocol timing artifacts with no a priori knowledge. Since our approach uses symbolic reasoning, an important question is how to best translate continuous data observations to symbolic data. This translation is problematic when observation variance makes continuous to symbolic translation unreliable. We examine this problem and show that the HMMs we infer compensate automatically for significant observation jitter and symbol misclassification. Experimental verification is presented.

AB - Recent research has exposed timing side channel vulnerabilities in many security applications. Hidden Markov models (HMMs) have used timing data to extract passwords from cryptographically protected communications tunnels. We extend that work to show how HMM models of protocols can be extracted directly from observations of protocol timing artifacts with no a priori knowledge. Since our approach uses symbolic reasoning, an important question is how to best translate continuous data observations to symbolic data. This translation is problematic when observation variance makes continuous to symbolic translation unreliable. We examine this problem and show that the HMMs we infer compensate automatically for significant observation jitter and symbol misclassification. Experimental verification is presented.

UR - http://www.scopus.com/inward/record.url?scp=80052466528&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80052466528&partnerID=8YFLogxK

U2 - 10.1109/IWCMC.2011.5982729

DO - 10.1109/IWCMC.2011.5982729

M3 - Conference contribution

SN - 9781424495399

T3 - IWCMC 2011 - 7th International Wireless Communications and Mobile Computing Conference

SP - 1310

EP - 1314

BT - IWCMC 2011 - 7th International Wireless Communications and Mobile Computing Conference

ER -

Bhanu H, Schwier J, Craven R, Ozcelik I, Griffin C, Brooks RR. Noise tolerant symbolic learning of Markov models of tunneled protocols. In IWCMC 2011 - 7th International Wireless Communications and Mobile Computing Conference. 2011. p. 1310-1314. 5982729. (IWCMC 2011 - 7th International Wireless Communications and Mobile Computing Conference). https://doi.org/10.1109/IWCMC.2011.5982729