Skip to main content

Highly Non-linear Feed-Forward Arbiter PUF Against Machine Learning Attacks

  • Conference paper
  • First Online:
VLSI Design and Test (VDAT 2022)

Abstract

Arbiter PUFs (APUFs) are a good choice for their lightweight configuration but vulnerable to Machine Learning (ML) based attacks. This paper presents a feed-forward PUF (FF PUF) to increase the resistivity by adding a non-linear component in the feed-forward loop. The non-linear component is designed by XORing the response of two consecutive stages of conventional FF PUF and feeding it as a challenge to an intermediate stage. To decrease the susceptibility to various ML-based attacks, the proposed feed-forward XOR PUF (FFXOR PUF) is designed by XORing the response of multiple FF PUFs. The performance of the proposed FFXOR PUF is compared with the existing APUF and XOR APUF. The minimum prediction accuracy of the proposed FFXOR PUF with 5 levels is achieved 51.6%(SVM) and 50.43%(ANN). Also, the training time is increased by 3.1 times in comparison with the conventional XOR APUF. Different PUF architectures such as APUF, XOR APUF and the proposed FFXOR PUF with 32-stages are implemented on Xilinx Zynq-7000 (Zedboard) FPGA.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Abadi, M., et al.: Tensorflow: a system for large-scale machine learning. In: Proceedings of the 12th USENIX Conference on Operating Systems Design and Implementation, pp. 265–283. OSDI 2016, USENIX Association, USA (2016)

    Google Scholar 

  2. Aseeri, A.O., Zhuang, Y., Alkatheiri, M.S.: A machine learning-based security vulnerability study on XOR PUFS for resource-constraint Internet of Things. In: 2018 IEEE International Congress on Internet of Things (ICIOT), pp. 49–56 (2018). https://doi.org/10.1109/ICIOT.2018.00014

  3. Avvaru, S.V.S., Zeng, Z., Parhi, K.K.: Homogeneous and heterogeneous feed-forward xor physical unclonable functions. IEEE Trans. Inf. Forens. Secur. 15, 2485–2498 (2020). https://doi.org/10.1109/TIFS.2020.2968113

    Article  Google Scholar 

  4. Avvaru, S.S., Parhi, K.K.: Effect of loop positions on reliability and attack resistance of feed-forward pufs. In: 2019 IEEE Computer Society Annual Symposium on VLSI (ISVLSI), pp. 366–371 (2019). https://doi.org/10.1109/ISVLSI.2019.00073

  5. Chollet, F., et al.: Keras (2015). https://keras.io

  6. Daniele, M., Sabrina, S., Francesco, D.P., Imrich, C.: Internet of things: Vision, applications and research challenges. Ad Hoc Netw. 10(7), 1497–1516 (2012)

    Article  Google Scholar 

  7. Das, B.P., Amrutur, B., Jamadagni, H.S., Arvind, N.V., Visvanathan, V.: Within-die gate delay variability measurement using reconfigurable ring oscillator. IEEE Trans. Semiconduct. Manufact. 22(2), 256–267 (2009). https://doi.org/10.1109/TSM.2009.2017662

    Article  Google Scholar 

  8. Das, B.P., Amrutur, B., Jamadagni, H.S., Arvind, N.V., Visvanathan, V.: Voltage and temperature-aware SSTA using neural network delay model. IEEE Trans. Semiconduct. Manufactur. 24(4), 533–544 (2011). https://doi.org/10.1109/TSM.2011.2163532

    Article  Google Scholar 

  9. Delvaux, J.: Machine-learning attacks on polypufs, ob-pufs, rpufs, lhs-pufs, and puf-fsms. IEEE Trans. Inf. Forens. Secur. 14(8), 2043–2058 (2019). https://doi.org/10.1109/TIFS.2019.2891223

  10. Ebrahimabadi, M., Younis, M., Lalouani, W., Karimi, N.: A novel modeling-attack resilient arbiter-PUF design. In: 2021 34th International Conference on VLSI Design and 2021 20th International Conference on Embedded Systems (VLSID), pp. 123–128 (2021). https://doi.org/10.1109/VLSID51830.2021.00026

  11. Gao, Y., et al.: Obfuscated challenge-response: a secure lightweight authentication mechanism for PUF-based pervasive devices. In: 2016 IEEE International Conference on Pervasive Computing and Communication Workshops (PerCom Workshops), pp. 1–6 (2016). https://doi.org/10.1109/PERCOMW.2016.7457162

  12. Gassend, B., Clarke, D., van Dijk, M., Devadas, S.: Controlled physical random functions. In: Proceedings of 18th Annual Computer Security Applications Conference, 2002, pp. 149–160 (2002). https://doi.org/10.1109/CSAC.2002.1176287

  13. Gassend, B., Clarke, D., van Dijk, M., Devadas, S.: Silicon physical random functions. In: Proceedings of the 9th ACM Conference on Computer and Communications Security, pp. 148–160. CCS 2002. Association for Computing Machinery, New York, NY, USA (2002). https://doi.org/10.1145/586110.586132

  14. Halak, B., Zwolinski, M., Mispan, M.S.: Overview of PUF-based hardware security solutions for the Internet of Things. In: 2016 IEEE 59th International Midwest Symposium on Circuits and Systems (MWSCAS), pp. 1–4 (2016). https://doi.org/10.1109/MWSCAS.2016.7870046

  15. Herder, C., Yu, M.D., Koushanfar, F., Devadas, S.: Physical unclonable functions and applications: a tutorial. Proc. IEEE 102(8), 1126–1141 (2014). https://doi.org/10.1109/JPROC.2014.2320516

    Article  Google Scholar 

  16. Ikezaki, Y., Nozaki, Y., Yoshikawa, M.: Deep learning attack for physical unclonable function. In: 2016 IEEE 5th Global Conference on Consumer Electronics, pp. 1–2 (2016). https://doi.org/10.1109/GCCE.2016.7800478

  17. Lim, D., Lee, J., Gassend, B., Suh, G., van Dijk, M., Devadas, S.: Extracting secret keys from integrated circuits. IEEE Trans. Very Large Scale Integr. (VLSI) Syst. 13(10), 1200–1205 (2005). https://doi.org/10.1109/TVLSI.2005.859470

  18. Rajan, A., Sankaran, S.: Lightweight and attack-resilient PUF for Internet of Things. In: 2020 IEEE International Symposium on Smart Electronic Systems (iSES) (Formerly iNiS), pp. 139–142 (2020). https://doi.org/10.1109/iSES50453.2020.00039

  19. Rostami, M., Majzoobi, M., Koushanfar, F., Wallach, D.S., Devadas, S.: Robust and reverse-engineering resilient PUF authentication and key-exchange by substring matching. IEEE Trans. Emerg. Top. Comput. 2(1), 37–49 (2014). https://doi.org/10.1109/TETC.2014.2300635

    Article  Google Scholar 

  20. Rührmair, U., Sehnke, F., Sölter, J., Dror, G., Devadas, S., Schmidhuber, J.: Modeling attacks on physical unclonable functions. In: 17th ACM Conference on Computer and Communications Security, pp. 237–249. CCS 2010. Association for Computing Machinery, New York, NY, USA (2010). https://doi.org/10.1145/1866307.1866335

  21. Rührmair, U., et al.: Efficient power and timing side channels for physical unclonable functions. In: Batina, L., Robshaw, M. (eds.) CHES 2014. LNCS, vol. 8731, pp. 476–492. Springer, Heidelberg (2014). https://doi.org/10.1007/978-3-662-44709-3_26

    Chapter  Google Scholar 

  22. Shah, N., Chatterjee, D., Sapui, B., Mukhopadhyay, D., Basu, A.: Introducing recurrence in strong PUFS for enhanced machine learning attack resistance. IEEE J. Emerg. Select. Top. Circ. Syst. 11(2), 319–332 (2021). https://doi.org/10.1109/JETCAS.2021.3075767

    Article  Google Scholar 

  23. Suh, G.E., Devadas, S.: Physical unclonable functions for device authentication and secret key generation. In: 2007 44th ACM/IEEE Design Automation Conference, pp. 9–14 (2007)

    Google Scholar 

  24. Wang, S.J., Chen, Y.S., Li, K.S.M.: Adversarial attack against modeling attack on PUFS. In: 2019 56th ACM/IEEE Design Automation Conference (DAC), pp. 1–6 (2019)

    Google Scholar 

  25. Yu, M.D., Hiller, M., Delvaux, J., Sowell, R., Devadas, S., Verbauwhede, I.: A lockdown technique to prevent machine learning on PUFS for lightweight authentication. IEEE Trans. Multi-Scale Comput. Syst. 2(3), 146–159 (2016). https://doi.org/10.1109/TMSCS.2016.2553027

    Article  Google Scholar 

  26. Zhuang, Y., Mursi, K.T., Li, G.: A challenge obfuscating interface for arbiter PUF variants against machine learning attacks. CoRR abs/2103.12935 (2021). https://arxiv.org/abs/2103.12935

Download references

Acknowledgements

This work is supported and funded by Science and Engineering Research Board (SERB), Department of Science and Technology, Government of India under the project grant number CRG/2021/007437.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Aranya Gupta .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Gupta, A., Manhas, S., Das, B.P. (2022). Highly Non-linear Feed-Forward Arbiter PUF Against Machine Learning Attacks. In: Shah, A.P., Dasgupta, S., Darji, A., Tudu, J. (eds) VLSI Design and Test. VDAT 2022. Communications in Computer and Information Science, vol 1687. Springer, Cham. https://doi.org/10.1007/978-3-031-21514-8_21

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-21514-8_21

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-21513-1

  • Online ISBN: 978-3-031-21514-8

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics