Toward parametric security analysis of machine learning based cyber forensic biometric systems

Koosha Sadeghi; Ayan Banerjee; Javad Sohankar; Sandeep Gupta

doi:10.1109/ICMLA.2016.168

Toward parametric security analysis of machine learning based cyber forensic biometric systems

Koosha Sadeghi, Ayan Banerjee, Javad Sohankar, Sandeep Gupta

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

11 Scopus citations

Abstract

Machine learning algorithms are widely used in cyber forensic biometric systems to analyze a subject's truthfulness in an interrogation. An analytical method (rather than experimental) to evaluate the security strength of these systems under potential cyber attacks is essential. In this paper, we formalize a theoretical method for analyzing the immunity of a machine learning based cyber forensic system against evidence tampering attack. We apply our theory on brain signal based forensic systems that use neural networks to classify responses from a subject. Attack simulation is run to validate our theoretical analysis results.

Original language	English (US)
Title of host publication	Proceedings - 2016 15th IEEE International Conference on Machine Learning and Applications, ICMLA 2016
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	626-631
Number of pages	6
ISBN (Electronic)	9781509061662
DOIs	https://doi.org/10.1109/ICMLA.2016.168
State	Published - Jan 31 2017
Event	15th IEEE International Conference on Machine Learning and Applications, ICMLA 2016 - Anaheim, United States Duration: Dec 18 2016 → Dec 20 2016

Other

Other	15th IEEE International Conference on Machine Learning and Applications, ICMLA 2016
Country/Territory	United States
City	Anaheim
Period	12/18/16 → 12/20/16

Keywords

Cyber forensic
Electroencephalogram
Machine learning
Security strength

ASJC Scopus subject areas

Artificial Intelligence
Computer Networks and Communications
Computer Science Applications

Access to Document

10.1109/ICMLA.2016.168

Cite this

Sadeghi, K., Banerjee, A., Sohankar, J., & Gupta, S. (2017). Toward parametric security analysis of machine learning based cyber forensic biometric systems. In Proceedings - 2016 15th IEEE International Conference on Machine Learning and Applications, ICMLA 2016 (pp. 626-631). Article 7838214 Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICMLA.2016.168

Toward parametric security analysis of machine learning based cyber forensic biometric systems. / Sadeghi, Koosha; Banerjee, Ayan; Sohankar, Javad et al.
Proceedings - 2016 15th IEEE International Conference on Machine Learning and Applications, ICMLA 2016. Institute of Electrical and Electronics Engineers Inc., 2017. p. 626-631 7838214.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Sadeghi, K, Banerjee, A, Sohankar, J & Gupta, S 2017, Toward parametric security analysis of machine learning based cyber forensic biometric systems. in Proceedings - 2016 15th IEEE International Conference on Machine Learning and Applications, ICMLA 2016., 7838214, Institute of Electrical and Electronics Engineers Inc., pp. 626-631, 15th IEEE International Conference on Machine Learning and Applications, ICMLA 2016, Anaheim, United States, 12/18/16. https://doi.org/10.1109/ICMLA.2016.168

@inproceedings{257dd8c8c5c542169cda7596d8a9e56d,

title = "Toward parametric security analysis of machine learning based cyber forensic biometric systems",

abstract = "Machine learning algorithms are widely used in cyber forensic biometric systems to analyze a subject's truthfulness in an interrogation. An analytical method (rather than experimental) to evaluate the security strength of these systems under potential cyber attacks is essential. In this paper, we formalize a theoretical method for analyzing the immunity of a machine learning based cyber forensic system against evidence tampering attack. We apply our theory on brain signal based forensic systems that use neural networks to classify responses from a subject. Attack simulation is run to validate our theoretical analysis results.",

keywords = "Cyber forensic, Electroencephalogram, Machine learning, Security strength",

author = "Koosha Sadeghi and Ayan Banerjee and Javad Sohankar and Sandeep Gupta",

year = "2017",

month = jan,

day = "31",

doi = "10.1109/ICMLA.2016.168",

language = "English (US)",

pages = "626--631",

booktitle = "Proceedings - 2016 15th IEEE International Conference on Machine Learning and Applications, ICMLA 2016",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

note = "15th IEEE International Conference on Machine Learning and Applications, ICMLA 2016 ; Conference date: 18-12-2016 Through 20-12-2016",

}

TY - GEN

T1 - Toward parametric security analysis of machine learning based cyber forensic biometric systems

AU - Sadeghi, Koosha

AU - Banerjee, Ayan

AU - Sohankar, Javad

AU - Gupta, Sandeep

PY - 2017/1/31

Y1 - 2017/1/31

N2 - Machine learning algorithms are widely used in cyber forensic biometric systems to analyze a subject's truthfulness in an interrogation. An analytical method (rather than experimental) to evaluate the security strength of these systems under potential cyber attacks is essential. In this paper, we formalize a theoretical method for analyzing the immunity of a machine learning based cyber forensic system against evidence tampering attack. We apply our theory on brain signal based forensic systems that use neural networks to classify responses from a subject. Attack simulation is run to validate our theoretical analysis results.

AB - Machine learning algorithms are widely used in cyber forensic biometric systems to analyze a subject's truthfulness in an interrogation. An analytical method (rather than experimental) to evaluate the security strength of these systems under potential cyber attacks is essential. In this paper, we formalize a theoretical method for analyzing the immunity of a machine learning based cyber forensic system against evidence tampering attack. We apply our theory on brain signal based forensic systems that use neural networks to classify responses from a subject. Attack simulation is run to validate our theoretical analysis results.

KW - Cyber forensic

KW - Electroencephalogram

KW - Machine learning

KW - Security strength

UR - http://www.scopus.com/inward/record.url?scp=85015427027&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85015427027&partnerID=8YFLogxK

U2 - 10.1109/ICMLA.2016.168

DO - 10.1109/ICMLA.2016.168

M3 - Conference contribution

AN - SCOPUS:85015427027

SP - 626

EP - 631

BT - Proceedings - 2016 15th IEEE International Conference on Machine Learning and Applications, ICMLA 2016

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 15th IEEE International Conference on Machine Learning and Applications, ICMLA 2016

Y2 - 18 December 2016 through 20 December 2016

ER -

Toward parametric security analysis of machine learning based cyber forensic biometric systems

Abstract

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this