Nothing Special   »   [go: up one dir, main page]
Skip to main content
Springer Nature Link
Log in

A Resource-Efficient Binary CNN Implementation for Enabling Contactless IoT Authentication

  • Published:
Journal of Hardware and Systems Security Aims and scope Submit manuscript

Abstract

Access control is already an integral part of the Internet of Things (IoT) to prevent unauthorized use of systems. However, in the post-pandemic world, contactless authentication is desired for multi-user in-person systems. Biometric key-based hardware obfuscation can enable user-specific access control for IoT devices with added protection against piracy, reverse engineering, and hardware tampering. Biometric key-based unlocking of devices relies on various feature generation and classification tasks, for which convolutional neural networks (CNN) have demonstrated state-of-the-art effectiveness. In this regard, CNN-based contactless biometric template submission (e.g., face) can be a potential candidate. However, for resource-constrained devices (i.e., IoT), especially those with limited hardware capabilities, might struggle to efficiently execute CNN-based models due to their intensive memory access patterns, operational delays, communication bandwidth, and power consumption. Exploiting the recent advancements in information flow theory in neural networks and binary features, in this paper, we propose a CNN-based biometric system where binary weights and activations are used to generate compact yet, meaningful binary biometric features to enable computation on resource-constrained edge devices. We implement the proposed framework and a conventional CNN on a face dataset in an FPGA as a proof-of-concept and obtain a classification accuracy of 96%, and reduced resource requirements on average 40% compared to a typical CNN. We also validate the effectiveness of the proposed system with two individual face datasets, which reflect two common prevailing challenges — training on samples with low resolution and much fewer training samples, where we obtain 95% and 83% classification accuracy, respectively. Finally, we compare the hardware-level implementation of binary and legacy CNN and observe significant advantages in storage, power, and performance.

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

Access this article

Log in via an institution

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

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

Notes

  1. In this paper, the term “legacy CNN” refers to typical CNNs that process and produce real-valued features.

  2. Note that our paper does not investigate the learning through information bottleneck (IB) framework.

References

  1. Shomaji S, Guo Z, Ganji F, Karimian N, Woodard D, Forte D (2021) Blocker: A biometric locking paradigm for IoT and the connected person. Journal of hardware and systems security, Springer Nature 5:223–236

    Article  Google Scholar 

  2. Rahman MT et al (2020) The key is left under the mat: On the inappropriate security assumption of logic locking schemes. In: 2020 IEEE International symposium on HOST, IEEE, pp 262–272

  3. Sun Y, Liang D, Wang X, Tang X (2015) Deepid3: Face recognition with very deep neural networks. arXiv preprint arXiv:1502.00873

  4. Alzubaidi L et al (2021) Review of deep learning: Concepts, CNN architectures, challenges, applications, future directions. J Big Data 8:1–74

    Article  Google Scholar 

  5. Khan A et al (2020) A survey of the recent architectures of deep convolutional neural networks. Artif Intell Rev 53:5455–5516

    Article  Google Scholar 

  6. Sun Y, Wang X, Tang X (2014) Deep learning face representation from predicting 10,000 classes. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1891–1898

  7. Zhu Z, Luo P, Wang X, Tang X (2014) Deep learning and disentangling face representation by multi-view perceptron. In: Proc. NIPS

  8. Chen XW, Lin X (2014) Big data deep learning: Challenges and perspectives. IEEE Access 2:514–525

    Article  Google Scholar 

  9. Strubell E, Ganesh A, McCallum A (2019) Energy and policy considerations for deep learning in NLP. arXiv preprint arXiv:1906.02243

  10. Petscharnig S, Schöffmann K (2018) Binary convolutional neural network features off-the-shelf for image to video linking in endoscopic multimedia databases. Multimed Tools Appl 77(21):28,817–28,842

  11. Arroyo R et al (2016) Fusion and binarization of CNN features for robust topological localization across seasons. In: IROS, IEEE, pp 4656–4663

  12. Chen C, Veldhuis RN, Kevenaar TA, Akkermans AH (2009) Biometric quantization through detection rate optimized bit allocation. EURASIP J Adv Signal Process

  13. Fratric I, Ribaric S (2011) Local binary LDA for face recognition. In: European workshop on biometrics and identity management, Springer, pp 144–155

  14. Karimian N, Guo Z, Tehranipoor F, Woodard D, Tehranipoor M, Forte D (2018) Secure and reliable biometric access control for resource-constrained systems and IoT. arXiv preprint arXiv:1803.09710

  15. Kevenaar TAo (2005) Face recognition with renewable and privacy preserving binary templates. In: Fourth IEEE Workshop on AutoID, IEEE

  16. Pang Y, Tao D, Yuan Y, Li X (2008) Binary two-dimensional PCA. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics) 38(4):1176–1180

  17. Shomaji S, Ganji F, Woodard D, Forte D (2019) Hierarchical bloom filter framework for security, space-efficiency, and rapid query handling in biometric systems. In: IEEE International conference on BTAS, IEEE

  18. Lu X, Wang H et al (2019) Learning a deep vector quantization network for image compression. IEEE Access 7:118,815–118,825

  19. Jebadurai J, Peter JD (2018) Super-resolution of retinal images using multi-kernel SVR for IoT healthcare applications. Future Generation Comput Syst 83:338–346

    Article  Google Scholar 

  20. Wagner R, Thom M, Schweiger R, Palm G, Rothermel A (2013) Learning convolutional neural networks from few samples. In: The 2013 International joint conference on neural networks, IEEE

  21. Forte D, Bhunia S, Tehranipoor MM (2017) Hardware protection through obfuscation. Springer

    Book  Google Scholar 

  22. Suh GE, Devadas S (2007) Physical unclonable functions for device authentication and secret key generation. In: 2007 44th ACM/IEEE Design automation conference, IEEE, pp 9–14

  23. Karimian N et al (2017) Highly reliable key generation from electrocardiogram (ECG). IEEE Trans Biomed Eng 64(6):1400–1411

    Article  Google Scholar 

  24. Ganji F, Karimian N, Woodard D, Forte D (2019) Leave adversaries in the dark- blocker: Secure and reliable biometric access control. J Homeland Defense Security Inf Anal Center (HDIAC) 6(1):4–8

    Google Scholar 

  25. Alaql A, Hoque T, Forte D, Bhunia S (2019) Quality obfuscation for error-tolerant and adaptive hardware IP protection. In: 2019 IEEE 37th VLSI Test Symposium (VTS), IEEE, pp 1–6

  26. Hoque T, Chakraborty RS, Bhunia S (2020) Hardware obfuscation and logic locking: A tutorial introduction. IEEE Design & Test 37(3):59–77

    Article  Google Scholar 

  27. Karimian N, Tehranipoor M, Woodard D, Forte D (2019) Unlock your heart: Next generation biometric in resource-constrained healthcare systems and IoT. IEEE Access 7:49,135–49,149

  28. Mohamed M, Abou-Elsoud M, Eid M (2011) Automated face recogntion system: Multi-input databases. In: International conference on computer engineering & systems, IEEE, pp 273–280

  29. Li Q, Sun Z, He R, Tan T (2017) Deep supervised discrete hashing. In: Advances in neural information processing systems, pp 2482–2491

  30. Shen F, Shen C, Liu W, Tao Shen H (2015) Supervised discrete hashing. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 37–45

  31. Ghasemzadeh M, Samragh M et al (2018) Rebnet: Residual binarized neural network. In: IEEE 26th Annual international symposium on FCCM

  32. Rastegari M, Ordonez V, Redmon J, Farhadi A (2016) Xnor-net: Imagenet classification using binary convolutional neural networks pp 525–542

  33. Courbariaux M et al (2016) Binarized neural networks: Training deep neural networks with weights and activations constrained to+ 1 or-1. arXiv preprint arXiv:1602.02830

  34. Li M et al (2018) Learning convolutional networks for content-weighted image compression. In: Proceedings of the IEEE conference on CVPR, pp 3214–3223

  35. Cao Y et al (2016) Deep quantization network for efficient image retrieval. In: Thirtieth AAAI conference on artificial intelligence

  36. Zhuang B et al (2019) Structured binary neural networks for accurate image classification and semantic segmentation. In: 2019 IEEE/CVF CVPR, pp 413–422. https://doi.org/10.1109/CVPR.2019.00050

  37. Bulat A et al (2019) Improved training of binary networks for human pose estimation and image recognition. arXiv:1904.05868. https://api.semanticscholar.org/CorpusID:118645462

  38. Liu Z, Shen Z, Savvides M, Cheng KT (2020) Reactnet: Towards precise binary neural network with generalized activation functions. In: Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XIV 16, Springer, pp 143–159

  39. Neary P (2018) Automatic hyperparameter tuning in deep convolutional neural networks using asynchronous reinforcement learning. In: 2018 IEEE International conference on cognitive computing (ICCC), IEEE, pp 73–77

  40. Chen XY, Peng XY, Peng Y, Li JB (2016) The classification of synthetic aperture radar image target based on deep learning. J Inf Hiding Multimed Signal Process 7(6)

  41. Schwegmann CP, Kleynhans W, Salmon BP, Mdakane LW, Meyer RG (2016) Very deep learning for ship discrimination in synthetic aperture radar imagery. In: IGARSS, IEEE, pp 104–107

  42. Hutter F, Kotthoff L, Vanschoren J (2019) Hyperparameter optimization chapter in automated machine learning. Springer

    Google Scholar 

  43. Yu T, Zhu H (2020) Hyper-parameter optimization: a review of algorithms and applications. arXiv preprint arXiv:2003.05689

  44. Pan SJ, Yang Q (2009) A survey on transfer learning. IEEE Trans Knowl Data Eng 22(10):1345–1359

    Article  Google Scholar 

  45. Zeiler MD, Fergus R (2014) Visualizing and understanding convolutional networks pp 818–833

  46. Tishby N, Zaslavsky N (2015) Deep learning and the information bottleneck principle. In: IEEE Information theory workshop (ITW), IEEE, pp 1–5

  47. Yu S, Wickstrøm K, Jenssen R, Principe JC (2020) Understanding convolutional neural networks with information theory. IEEE NNLS

  48. Campadelli P, Casiraghi E, Ceruti C, Rozza A (2015) Intrinsic dimension estimation: Relevant techniques and a benchmark framework. Math Problems Eng 2015

  49. Spacek L (2007) Collection of facial images: Faces94. University of Essex, United Kingdom, Computer Vision Science and Research Projects

    Google Scholar 

  50. Phillips PJ et al (2005) Overview of the face recognition grand challenge. In: 2005 IEEE CVPR), IEEE, vol 1, pp 947–954

  51. Hemery B et al (2010) Study on color spaces for single image enrolment face authentication. In: 2010 20th International conference on pattern recognition, IEEE, pp 1249–1252

  52. King DE (2009) Dlib-ml: a machine learning toolkit. J Mach Learn Res 10(Jul):1755–1758

  53. Lombardi G (2020) Intrinsic dimensionality estimation techniques. MATLAB Central File Exchange

  54. Beauchamp MJ, Hauck S, Underwood KD, Hemmert KS (2006) Embedded floating-point units in FPGAs. In: Proceedings of the 2006 ACM/SIGDA 14th international symposium on Field programmable gate arrays, pp 12–20

  55. Govindu G et al (2004) Analysis of high-performance floating-point arithmetic on FPGAs. In: 18th International parallel and distributed processing symposium, 2004., IEEE, p 149

  56. Moi SH, Yong PY (2017) A modified reed Solomon error correction codes for multimodal biometrics recognition. In: 3rd ICCAR, IEEE, pp 418–422

  57. Li T (2005) A general model for clustering binary data. In: Proceedings of the eleventh ACM SIGKDD international conference on Knowledge discovery in data mining, pp 188–197

  58. Al-Dabagh MZN, Alhabib M, Al-Mukhtar F (2018) Face recognition system based on kernel discriminant analysis, k-nearest neighbor and support vector machine. Int J Res Eng 5(3):335–338

    Article  Google Scholar 

  59. Snell J, Swersky K, Zemel R (2017) Prototypical networks for few-shot learning. In: Advances in neural information processing systems, pp 4077–4087

  60. Umuroglu Y, Fraser NJ et al (2017) Finn: A framework for fast, scalable binarized neural network inference. In: Proceedings of the 2017 ACM/SIGDA international symposium on field-programmable gate arrays, ACM, FPGA ’17, pp 65–74

  61. Gomez-Barrero M, Drozdowski P et al (2021) Biometrics in the era of COVID-19: Challenges and opportunities. arXiv preprint arXiv:2102.09258

  62. Burt C (2018) “Smile-to-pay” facial recognition now at 300 locations in China: Biometric update

  63. Regazzoni F, Bhasin S, Pour et al (2020) Machine learning and hardware security: Challenges and opportunities-invited talk. In: 2020 IEEE/ACM International conference on computer aided design (ICCAD), IEEE, pp 1–6

  64. Faezi S, Yasaei R, Barua A, Al Faruque MA (2021) Brain-inspired golden chip free hardware trojan detection. IEEE Trans Inf Forensics Security 16:2697–2708

    Article  Google Scholar 

  65. Chang YJ, Chen TH, Zhang WD (2010) Biometrics-based cryptographic key generation system and method. US Patent 7,804,956

  66. Wu L, Liu X, Yuan S, Xiao P (2010) A novel key generation cryptosystem based on face features. In: IEEE 10th International conference on signal processing proceedings, IEEE, pp 1675–1678

  67. Chen B, Chandran V (2007) Biometric based cryptographic key generation from faces. In: 9th Biennial conference of the Australian pattern recognition society on DICTA, IEEE, pp 394–401

  68. Yang W, Wang S, Hu J, Zheng G, Chaudhry J, Adi E, Valli C (2018) Securing mobile healthcare data: A smart card based cancelable finger-vein bio-cryptosystem. IEEE Access 6:36,939–36,947

  69. Rathgeb C, Breitinger F, Busch C, Baier H (2014) On application of bloom filters to iris biometrics. IET Biomet 3(4):207–218

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. University of Kansas, 66045, Lawrence, KS, USA

    Mahmudul Hasan, Tamzidul Hoque & Sumaiya Shomaji

  2. Worcester Polytechnic Institute, 01609, Worcester, MA, USA

    Fatemeh Ganji

  3. University of Florida, 32611, Gainesville, FL, USA

    Damon Woodard & Domenic Forte

Authors
  1. Mahmudul Hasan
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Tamzidul Hoque
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Fatemeh Ganji
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Damon Woodard
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Domenic Forte
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Sumaiya Shomaji
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Mahmudul Hasan.

Ethics declarations

Funding

Not applicable.

Competing Interests

The authors declare no competing interests.

Author Contributions

DF and SS generated the idea. MH, SS, and TH conducted the experiments along with preparing the manuscript. Reviewed by all.

Data Availability

Data and materials are available upon request.

Ethical Approval

Not applicable.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Hasan, M., Hoque, T., Ganji, F. et al. A Resource-Efficient Binary CNN Implementation for Enabling Contactless IoT Authentication. J Hardw Syst Secur 8, 160–173 (2024). https://doi.org/10.1007/s41635-024-00153-7

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s41635-024-00153-7

Keywords

Search

Navigation