Advertisement

Embedded Classifiers for Energy-Constrained IoT Network Security

  • Jennifer Hasler
Chapter

Abstract

We discuss the impact of physical computing techniques to classifying network security issues for ultra-low power networked IoT devices. Energy-constrained IoT systems, such as wearable devices, are already sensor rich and processing/computation constrained. The digital energy efficiency wall constrains the amount of signal processing possible at energy-constrained nodes. One rarely has any computational resources left to consider network security, leaving devices exposed. Fortunately many of these devices have infrequent wireless communication with very constrained command structures, but they still exhibit a system vulnerability, particularly when monitoring or controlling physical infrastructure. Physical computing approaches enable at least a factor of 1000 improvement in computational energy efficiency empowering a new generation of local computational structures for embedded IoT devices. These techniques offer computational capability to address network security concerns.

Notes

Acknowledgements

This chapter resulted from a conference on IoT and embedded network device security in Paris in July 2017. My first exposure to security of embedded network devices started in Paris, not too far from the conference in 2017, when I (J. Hasler) visited Francois Bayen and his family in Paris in 1991 as a young graduate student. We had a number of technical discussions on embedded integrated circuit (IC) security related to a number of his European projects. These discussions gave me the background and interest to dig deeper in these areas when the time came; I am thankful for everything I learned from him during that visit and later visits. Twenty-six years later these discussions have come full circle. Writing this chapter on security of embedded devices, particularly FPAA devices, has brought me back to the knowledge source. Their family has remained close friends with my family to this day.

References

  1. 1.
    V. Asharani, B.N. Veerappa, M. Rafi, Security evaluation of pattern classifiers in adversarial environments. Int. J. Comput. Sci. Mobile Comput. 4(4), 768–774 (2015)Google Scholar
  2. 2.
    T. Bakhshi, B. Ghita, On internet traffic classification: a two-phased machine learning approach. J Comput. Netw. Commun. 1–21 (2016)CrossRefGoogle Scholar
  3. 3.
    R. Bar-Yanai, M. Langberg, D. Peleg, L. Roditty, Realtime classification for encrypted traffic, in SEA (2010), pp. 373–385Google Scholar
  4. 4.
    A. Basu, S. Brink, C. Schlottmann, S. Ramakrishnan, C. Petre, S. Koziol, F. Baskaya, C. Twigg, P. Hasler, A floating-gate-based field-programmable analog array. IEEE J. Solid-State Circuits 45(9), 1781–1794 (2010)CrossRefGoogle Scholar
  5. 5.
    B. Biggio, G. Fumera, F. Roli, Security evaluation of pattern classifiers under attack. IEEE Trans. Knowl. Data Eng. 26(4), 984–996 (2014)CrossRefGoogle Scholar
  6. 6.
    C. Bormann, M. Ersue, A. Ericsson, Terminology for constrained-node networks, in RFC 7228. Internet Engineering Task Force (IETF) (2014)Google Scholar
  7. 7.
    A.A. Cardenas, J.S. Baras, Evaluation of classifiers: practical considerations for security applications (2006)Google Scholar
  8. 8.
    R. Chakraborty, C. Lamech D. Acharyya, J. Plusquellic, A transmission gate physical unclonable function and on-chip voltage- to-digital conversion technique, in IEEE DAC (2013), pp. 59:1–59:10Google Scholar
  9. 9.
    M. Collins, J. Hasler, S. George, An open-source toolset enabling analog–digital software codesign. J. Low Power Electron. Appl. 6(1), 3 (2016)CrossRefGoogle Scholar
  10. 10.
    A. Dainotti, A. Pescape, K.C. Claffy, Issues and future directions in traffic classification. IEEE Netw. 26(1), 35–40 (2012)CrossRefGoogle Scholar
  11. 11.
    S. George, S. Kim, S. Shah, J. Hasler, M. Collins, F. Adil, R, Wunderlich, S. Nease, S. Ramakrishnan, A programmable and configurable mixed-mode FPAA SoC. IEEE Trans. Very Large Scale Integr. 24(6), 2253–2261 (2016)Google Scholar
  12. 12.
    J. Hasler, Opportunities in physical computing driven by analog realization, in IEEE ICRC, San Diego (2016)Google Scholar
  13. 13.
    J. Hasler, Analog Abstraction, Computation, and Numerical Analysis. Accepted to ISCAS 2018, Florance, May 2018Google Scholar
  14. 14.
    J. Hasler, B. Marr, Finding a roadmap to achieve large neuromorphic hardware systems. Front. Neuromorphic Eng. (2013), 1–29.  https://doi.org/10.3389/fnins.2013.00118
  15. 15.
    J. Hasler, S. Shah, SoC FPAA hardware implementation of a VMM+WTA embedded learning classifier, in IEEE ECAS (2018)Google Scholar
  16. 16.
    J. Hasler, S. Shah, Security implications for ultra-low power configurable SoC FPAA embedded systems. J. Low-Power Electron. Appl. 8(2), 1–18 (2018)CrossRefGoogle Scholar
  17. 17.
    P. Hasler, C. Diorio, B.A. Minch, C.A. Mead, Single transistor learning synapses, in Advances in Neural Information Processing Systems, ed. by G. Tesauro, D.S. Touretzky, T.K. Leen, vol. 7 (MIT Press, Cambridge, 1994), pp. 817–824Google Scholar
  18. 18.
    P. Hasler, C. Diorio, B. Minch, C. Mead, Single transistor learning synapse with long term storage. IEEE Int. Symp. Circuits Syst. 3, 1660–1663 (1995)Google Scholar
  19. 19.
    P. Hasler, B. Minch, C. Diorio, Adaptive circuits using pFET floating-gate devices, in Advanced Research in VLSI (1999), pp. 215–229Google Scholar
  20. 20.
    J. Hasler, S. Kim, F. Adil, Scaling floating-gate devices predicting behavior for programmable and configurable circuits and systems. J. Low Power Electron. Appl. 6(3), 13 (2016)CrossRefGoogle Scholar
  21. 21.
    J. Hasler, A. Natarajan, S. Shah, S. Kim, SoC FPAA immersed junior level circuits course, in MSE (2017)Google Scholar
  22. 22.
    T. Heer, O. Garcia-Morchon, R. Hummen, S.L. Keoh, S.S. Kumar, K. Wehrle, Security challenges in the IP-based internet of things? Wirel. Pers. Commun. 61(3), 527–542 (2011)CrossRefGoogle Scholar
  23. 23.
    Z. Khorshidpour, S. Hashemi, A. Hamzeh, Learning a secure classifier against evasion attack, in IEEE Data Mining Workshops (2016), pp. 295–302Google Scholar
  24. 24.
    S. Kim, J. Hasler, S. George, Integrated floating-gate programming environment for system-level ICs. EEE Trans. Very Large Scale Integr. 24(6), 2244–2252 (2016)Google Scholar
  25. 25.
    S. Kim, S. Shah, J. Hasler, Calibration of floating-gate SoC FPAA system. IEEE Trans. Very Large Scale Integr. (2017)Google Scholar
  26. 26.
    J. King, A.I. Awad, A distributed security mechanism for resource-constrained IoT devices. Informatica 40, 133–143 (2016)Google Scholar
  27. 27.
    C. Mead, Neuromorphic electronic systems. Proc. IEEE 78, 1629–1636 (1990)CrossRefGoogle Scholar
  28. 28.
    N. Muthumeenakshi, S. Sharma, M. Farjanaaameera, R. Rajaprabha, LSI design of low cost (PUF) physical unclonable function using FPGA and highly secured clock network. IOSR J. VLSI Signal Process. 4(1), 16–21 (2014)CrossRefGoogle Scholar
  29. 29.
    G. Oikonomou, I. Phillips, Experiences from porting the Contiki operating system to a popular hardware platform, in IEEE DCOSS Workshop, Barcelona (2011)Google Scholar
  30. 30.
    T. Omrani, A. Dallali, B.C. Rhaimi, J. Fattahi, Fusion of ANN and SVM classifiers for network attack detection, in Sciences and Techniques of Automatic Control (2018)Google Scholar
  31. 31.
    R. Roman, P. Najera, J. Lopez, Securing the Internet of Things. IEEE Comput. 44(9), 51–58 (2011)CrossRefGoogle Scholar
  32. 32.
    T. Saha, V. Sehwag, TV-PUF : a fast lightweight analog physical unclonable function, in IEEE Nanoelectric and Information Systems (2016)Google Scholar
  33. 33.
    C. Schlottmann, S. Shapero, S. Nease, P. Hasler, A digitally enhanced dynamically reconfigurable analog platform for low-power signal processing. IEEE J. Solid-State Circuits 47(9), 2174–2184 (2012)CrossRefGoogle Scholar
  34. 34.
    P. Velan, M. Cermak, P. Celeda, M. Drasar, A survey of methods for encrypted traffic classification and analysis. Int. J. Netw. Manage. 25(5), 355–374 (2014)CrossRefGoogle Scholar
  35. 35.
    Z. Wang, The applications of deep learning on traffic identificationGoogle Scholar
  36. 36.
    Z. Wang, Y. Chen, A. Patil, J. Jayabalan, X. Zhang, C.H. Chang, A. Basu, Current mirror array: a novel circuit topology for combining physical unclonable function and machine learning, in IEEE TCAS I (2017)Google Scholar
  37. 37.
    T. Xu, M. Potkonjak, Robust and flexible FPGA-based digital PUF, in FPL (2014)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.Georgia Institute of TechnologyAtlantaUSA

Personalised recommendations