Skip to main content

2019 | OriginalPaper | Buchkapitel

The Feasibility of Deep Learning Use for Adversarial Model Extraction in the Cybersecurity Domain

verfasst von : Michał Choraś, Marek Pawlicki, Rafał Kozik

Erschienen in: Intelligent Data Engineering and Automated Learning – IDEAL 2019

Verlag: Springer International Publishing

Aktivieren Sie unsere intelligente Suche um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

Machine learning algorithms found their way into a surprisingly wide range of applications, providing utility and allowing for insights gathered from data in a way never before possible. Those tools, however, have not been developed with security in mind. A deployed algorithm can meet a multitude of risks in the real world. This work explores one of those risks - the feasibility of an exploratory attack geared towards stealing an algorithm used in the cybersecurity domain. The process we have used is thoroughly explained and the results are promising.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literatur
1.
Zurück zum Zitat Papernot, N., McDaniel, P., Sinha, A., Wellman, M.P.: SoK: security and privacy in machine learning. In: 2018 IEEE European Symposium on Security and Privacy (EuroS P), pp. 399–414, April 2018 Papernot, N., McDaniel, P., Sinha, A., Wellman, M.P.: SoK: security and privacy in machine learning. In: 2018 IEEE European Symposium on Security and Privacy (EuroS P), pp. 399–414, April 2018
2.
Zurück zum Zitat Ateniese, G., Felici, G., Mancini, L.V., Spognardi, A., Villani, A., Vitali, D.: Hacking smart machines with smarter ones: how to extract meaningful data from machine learning classifiers. CoRR, abs/1306.4447 (2013) Ateniese, G., Felici, G., Mancini, L.V., Spognardi, A., Villani, A., Vitali, D.: Hacking smart machines with smarter ones: how to extract meaningful data from machine learning classifiers. CoRR, abs/1306.4447 (2013)
3.
Zurück zum Zitat Chakraborty, A., Alam, M., Dey, V., Chattopadhyay, A., Mukhopadhyay, D.: Adversarial attacks and defences: a survey. CoRR, abs/1810.00069 (2018) Chakraborty, A., Alam, M., Dey, V., Chattopadhyay, A., Mukhopadhyay, D.: Adversarial attacks and defences: a survey. CoRR, abs/1810.00069 (2018)
4.
Zurück zum Zitat Liao, X., Ding, L., Wang, Y.: Secure machine learning, a brief overview. In: 2011 Fifth International Conference on Secure Software Integration and Reliability Improvement - Companion, pp. 26–29, June 2011 Liao, X., Ding, L., Wang, Y.: Secure machine learning, a brief overview. In: 2011 Fifth International Conference on Secure Software Integration and Reliability Improvement - Companion, pp. 26–29, June 2011
5.
Zurück zum Zitat Shi, Y., Sagduyu, Y., Grushin, A.: How to steal a machine learning classifier with deep learning. In: 2017 IEEE International Symposium on Technologies for Homeland Security (HST), pp. 1–5, April 2017 Shi, Y., Sagduyu, Y., Grushin, A.: How to steal a machine learning classifier with deep learning. In: 2017 IEEE International Symposium on Technologies for Homeland Security (HST), pp. 1–5, April 2017
8.
Zurück zum Zitat Shi, Y., Sagduyu, Y.E., Davaslioglu, K., Li, J.H.: Generative adversarial networks for black-box API attacks with limited training data. CoRR, abs/1901.09113 (2019) Shi, Y., Sagduyu, Y.E., Davaslioglu, K., Li, J.H.: Generative adversarial networks for black-box API attacks with limited training data. CoRR, abs/1901.09113 (2019)
9.
Zurück zum Zitat Quiring, E., Arp, D., Rieck, K.: Forgotten siblings: unifying attacks on machine learning and digital watermarking. In: 2018 IEEE European Symposium on Security and Privacy (EuroS P), pp. 488–502, April 2018 Quiring, E., Arp, D., Rieck, K.: Forgotten siblings: unifying attacks on machine learning and digital watermarking. In: 2018 IEEE European Symposium on Security and Privacy (EuroS P), pp. 488–502, April 2018
11.
12.
Zurück zum Zitat Abadi, M., et al.: TensorFlow: large-scale machine learning on heterogeneous systems (2015). Software tensorflow.org Abadi, M., et al.: TensorFlow: large-scale machine learning on heterogeneous systems (2015). Software tensorflow.​org
Metadaten
Titel
The Feasibility of Deep Learning Use for Adversarial Model Extraction in the Cybersecurity Domain
verfasst von
Michał Choraś
Marek Pawlicki
Rafał Kozik
Copyright-Jahr
2019
DOI
https://doi.org/10.1007/978-3-030-33617-2_36