ANN Feature Vector Extraction Based Attack Method for Flip-Flop Based Arbiter Physical Unclonable Function

Xuejiao MA; Gang LI

doi:10.11999/JEIT210614

Volume 43 Issue 9

Sep. 2021

Turn off MathJax

Article Contents

Article Navigation > Journal of Electronics & Information Technology > 2021 > 43(9): 2498-2507

Xuejiao MA, Gang LI. ANN Feature Vector Extraction Based Attack Method for Flip-Flop Based Arbiter Physical Unclonable Function[J]. Journal of Electronics & Information Technology, 2021, 43(9): 2498-2507. doi: 10.11999/JEIT210614

Citation:

Xuejiao MA, Gang LI. ANN Feature Vector Extraction Based Attack Method for Flip-Flop Based Arbiter Physical Unclonable Function[J]. Journal of Electronics & Information Technology, 2021, 43(9): 2498-2507. doi: 10.11999/JEIT210614

Citation:

PDF( 3545 KB)

ANN Feature Vector Extraction Based Attack Method for Flip-Flop Based Arbiter Physical Unclonable Function

doi: 10.11999/JEIT210614 cstr: 32379.14.JEIT210614

Xuejiao MA¹,
Gang LI^{2
,
,}

1.
School of Data Science and Artificial Intelligence, Wenzhou University of Technology, Wenzhou 325035, China
2.
College of Electrical and Electronic Engineering, Wenzhou University, Wenzhou 325035, China

Funds: The National Key Research and Development Program of China (2018YFB2202100), The National Natural Science Foundation of China (61874078, 61904125), The Wenzhou Basic Scientific Research Projects (G20190006, G20190003)

Received Date: 2021-06-22
Rev Recd Date: 2021-08-12

Available Online: 2021-08-23

Publish Date: 2021-09-16

Abstract

Abstract

In order to evaluate the security of Physical Unclonable Function (PUF), it is necessary to put forward corresponding attack methods for different PUF structures. By studying the structure and working mechanism of Flip-Flop based Arbiter Physical Unclonable Function (FF-APUF), an effective attack method against FF-APUF is proposed based on Artificial Neural Network (ANN) in this paper. Firstly, according to the circuit structure, the delay model of FF-APUF is established by using multidimensional array. Secondly, all binary challenge bits are divided by two adjacent bits which are converted to a decimal, and then the challenges are expressed as a row vector to extract the feature vector. Finally, based on the extracted feature vectors, the attack model is constructed by ANN, and the optimal parameters are obtained by back propagation algorithm. The experimental results show that the prediction accuracy of the proposed method is higher than other three common machine learning methods under the same conditions. The attack advantage is more obvious, especially when the number of Challenge Response Pairs (CRP) is less and the bit number of challenges is large. For example, when the number of challenge bit is 128, and the number of CRPs is 100 and 500, the average attack prediction accuracy increased by 36.0% and 16.1% respectively. In addition, the proposed method has good robustness and scalability, and the maximum difference of attack prediction rate and reliability is only 0.32% under different noise.

FullText(HTML)

References(18)

References

[1]	LI Gang, WANG Pengjun, MA Xuejiao, et al. A multimode configurable physically unclonable function with bit-instability-screening and power-gating strategies[J]. IEEE Transactions on Very Large Scale Integration (VLSI) Systems, 2021, 29(1): 100–111. doi: 10.1109/TVLSI.2020.3030945
[2]	YAN Wei, TEHRANIPOOR F, and CHANDY J A. PUF-based fuzzy authentication without error correcting codes[J]. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2017, 36(9): 1445–1457. doi: 10.1109/TCAD.2016.2638445
[3]	USMANI M A, KESHAVARZ S, MATTHEWS E, et al. Efficient PUF-based key generation in FPGAs using per-device configuration[J]. IEEE Transactions on Very Large Scale Integration (VLSI) Systems, 2019, 27(2): 364–375. doi: 10.1109/TVLSI.2018.2877438
[4]	汪鹏君, 李乐薇, 郑雁公, 等. 基于气敏传感器的高稳态物理不可克隆函数发生器[J]. 电子与信息学报, 2021, 43(6): 1596–1602. doi: 10.11999/JEIT201104 WANG Pengjun, LI Lewei, ZHENG Yangong, et al. High steady-state physical unclonable function generator based on gas sensors[J]. Journal of Electronics &Information Technology, 2021, 43(6): 1596–1602. doi: 10.11999/JEIT201104
[5]	徐金甫, 吴缙, 李军伟, 等. 基于敏感度混淆机制的控制型物理不可克隆函数研究[J]. 电子与信息学报, 2019, 41(7): 1601–1609. doi: 10.11999/JEIT180775 XU Jinfu, WU Jin, LI Junwei, et al. Controlled physical unclonable function research based on sensitivity confusion mechanism[J]. Journal of Electronics &Information Technology, 2019, 41(7): 1601–1609. doi: 10.11999/JEIT180775
[6]	LIM D. Extracting secret keys from integrated circuits[D]. [Ph. D. dissertation], Massachusetts Institute of Technology, 2004.
[7]	RÜHRMAIR U, SÖLTER J, SEHNKE F, et al. PUF modeling attacks on simulated and silicon data[J]. IEEE Transactions on Information Forensics and Security, 2013, 8(11): 1876–1891. doi: 10.1109/TIFS.2013.2279798
[8]	SUH G E and DEVADAS S. Physical unclonable functions for device authentication and secret key generation[C]. The 44th ACM/IEEE Design Automation Conference, San Diego, USA, 2007: 9–14. doi: 10.1145/1278480.1278484.
[9]	MAITI A and SCHAUMONT P. Improving the quality of a physical unclonable function using configurable ring oscillators[C]. 2009 International Conference on Field Programmable Logic and Applications, Prague, Czech Republic, 2009: 703–707. doi: 10.1109/FPL.2009.5272361.
[10]	SAHOO D P, NGUYEN P H, MUKHOPADHYAY D, et al. A case of lightweight PUF constructions: Cryptanalysis and machine learning attacks[J]. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2015, 34(8): 1334–1343. doi: 10.1109/TCAD.2015.2448677
[11]	NGUYEN P H, SAHOO D P, JIN Chenglu, et al. The interpose PUF: Secure PUF design against state-of-the-art machine learning attacks[J]. IACR Transactions on Cryptographic Hardware and Embedded Systems, 2019, 2019(4): 243–290. doi: 10.13154/tches.v2019.i4.243-290
[12]	SAHOO D P, MUKHOPADHYAY D, CHAKRABORTY R S, et al. A multiplexer-based arbiter PUF composition with enhanced reliability and security[J]. IEEE Transactions on Computers, 2018, 67(3): 403–417. doi: 10.1109/TC.2017.2749226
[13]	GU Chongyan, LIU Weiqiang, CUI Yijun, et al. A Flip-Flop based Arbiter Physical Unclonable Function (APUF) design with high entropy and uniqueness for FPGA implementation[J]. IEEE Transactions on Emerging Topics in Computing, To be published. doi: 10.1109/TETC.2019.2935465.
[14]	AWANO H, IIZUKA T, and IKEDA M. PUFNet: A deep neural network based modeling attack for physically unclonable function[C]. 2019 IEEE International Symposium on Circuits and Systems, Sapporo, Japan, 2019: 1–4. doi: 10.1109/ISCAS.2019.8702431.
[15]	SANTIKELLUR P and CHAKRABORTY R S. A computationally efficient tensor regression network-based modeling attack on XOR arbiter PUF and its variants[J]. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2021, 40(6): 1197–1206. doi: 10.1109/TCAD.2020.3032624
[16]	SHI Junye, LU Yang, and ZHANG Jiliang. Approximation attacks on strong PUFs[J]. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2020, 39(10): 2138–2151. doi: 10.1109/TCAD.2019.2962115
[17]	CHATTERJEE D, MUKHOPADHYAY D, and HAZRA A. Interpose PUF can be PAC learned[OL]. https://www.researchgate.net/publication/343524875_Interpose_PUF_can_be_PAC_Learned?channel=doi&linkId=5f2e86d5458515b7290d567f&showFulltext=true. 2020.
[18]	CHAKRABORTY R S, JELDI R R, SAHA I, et al. Binary decision diagram assisted modeling of FPGA-based physically unclonable function by genetic programming[J]. IEEE Transactions on Computers, 2017, 66(6): 971–981. doi: 10.1109/TC.2016.2603498