Internet of Things. A Confluence of Many Disciplines by Augusto Casaca & Srinivas Katkoori & Sandip Ray & Leon Strous

Author:Augusto Casaca & Srinivas Katkoori & Sandip Ray & Leon Strous
Language: eng
Format: epub
ISBN: 9783030436056
Publisher: Springer International Publishing

PUF model

Encryption

Approach

Accuracy (%)

Cloning time (s)

4-XOR PUF

DES

LR (Brute)

43.75

53.9 s

RF (Brute)

42.2

1.8 s

MLP (Brute)

50.1

98.7 s

Ours (no decrypt)

55.5

86.7 s

Ours (no reconstr.)

57.9

65.7 s

Ours (full)

60.3

82.6 s

AES

LR (Brute)

40.62

49.9 s

RF (Brute)

48.43

1.3 s

MLP (Brute)

50.23

112.9 s

Ours (no decrypt)

57.6

93.1 s

Ours (no reconstr.)

59.7

81.4 s

Ours (full)

63.9

97.6 s

5 Conclusion and Future Work

In this work, we introduce and evaluate a novel, generative framework using based on a variational autoencoder to clone PUF models over an encrypted communication channel, which is a realistic scenario. We are, to the best of our knowledge, the first to address the problem of encrypted CRPs. We show that the use of the unsupervised pretraining using the proposed framework and training regimen allows us to successfully clone a given PUF model without the need for knowing the secret key used in the encryption protocol. Extensive experiments show that the proposed approach can generalize even with a limited number of CRPs and can show significantly higher cloning accuracy compared to brute force machine learning models. In the future, we aim to show that the proposed approach can generate or recover CRPs that are transmitted with obfuscation and noisy channels.

References

1.

Aman, M.N., Chua, K.C., Sikdar, B.: Hardware primitives-based security protocols for the internet of things. In: Cryptographic Security Solutions for the Internet of Things, pp. 117–141. IGI Global (2019)

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.