Attacking Arbiter PUFs Using Various Modeling Attack Algorithms: A Comparative Study

Yue Fang; Qingqing Ma; Chongyan Gu; Chenghua  Wang; Maire O'Neill; Weiqiang Liu

doi:10.1109/APCCAS.2018.8605618

Attacking Arbiter PUFs Using Various Modeling Attack Algorithms: A Comparative Study

Yue Fang, Qingqing Ma, Chongyan Gu, Chenghua Wang, Maire O'Neill, Weiqiang Liu

School of Electronics, Electrical Engineering and Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Citation (Scopus)

173 Downloads (Pure)

Abstract

In this paper, we investigate the effectiveness of four different modeling attack algorithms, including Logistic Regression (LR), Naïve Bayes, AdaBoost and Covariance Matrix Adaptation Evolutionary Strategies (CMA-ES), on attacking arbiter physical unclonable functions (APUFs). A comparison of experimental results using theses algorithms is presented. The results show that the performance of the algorithms is related to the number of training data, the noise level involved in the APUF design and the number of stages in the generation of each bit response. It is found that the mainstream LR and CMA-ES are worse for a small number of data compared with Naïve Bayes and AdaBoost.

Original language	English
Title of host publication	2018 IEEE Asia Pacific Conference on Circuits and Systems (APCCAS)
Publisher	IEEE
Pages	394-397
Number of pages	4
ISBN (Electronic)	978-1-5386-8240-1
DOIs	https://doi.org/10.1109/APCCAS.2018.8605618 https://doi.org/10.1109/APCCAS.2018.8605618
Publication status	Published - 2019
Event	14th IEEE Asia Pacific Conference on Circuits and Systems, APCCAS 2018 - Chengdu, China Duration: 26 Oct 2018 → 30 Oct 2018

Conference

Conference	14th IEEE Asia Pacific Conference on Circuits and Systems, APCCAS 2018
Country	China
City	Chengdu
Period	26/10/2018 → 30/10/2018

Keywords

Machine Learning
Modeling Attacks
Physical Unclonable Functions

ASJC Scopus subject areas

Biomedical Engineering
Electrical and Electronic Engineering
Instrumentation

Access to Document

10.1109/APCCAS.2018.8605618Licence: Unspecified
10.1109/APCCAS.2018.8605618

A Comparative Study of Modeling Attacks On Arbiter PUF
Copyright 2018 IEEE. This work is made available online in accordance with the publisher’s policies. Please refer to any applicable terms of use of the publisher.
Accepted author manuscript, 1.31 MBLicence: Unspecified

Link to publication in Scopus

Fingerprint Dive into the research topics of 'Attacking Arbiter PUFs Using Various Modeling Attack Algorithms: A Comparative Study'. Together they form a unique fingerprint.

Cite this

Fang, Y., Ma, Q., Gu, C., Wang, C., O'Neill, M., & Liu, W. (2019). Attacking Arbiter PUFs Using Various Modeling Attack Algorithms: A Comparative Study. In 2018 IEEE Asia Pacific Conference on Circuits and Systems (APCCAS) (pp. 394-397). [8605618] IEEE . https://doi.org/10.1109/APCCAS.2018.8605618, https://doi.org/10.1109/APCCAS.2018.8605618

@inproceedings{79a9d3f9ceff44e08a3c7e56fa427139,

title = "Attacking Arbiter PUFs Using Various Modeling Attack Algorithms: A Comparative Study",

abstract = "In this paper, we investigate the effectiveness of four different modeling attack algorithms, including Logistic Regression (LR), Na{\"i}ve Bayes, AdaBoost and Covariance Matrix Adaptation Evolutionary Strategies (CMA-ES), on attacking arbiter physical unclonable functions (APUFs). A comparison of experimental results using theses algorithms is presented. The results show that the performance of the algorithms is related to the number of training data, the noise level involved in the APUF design and the number of stages in the generation of each bit response. It is found that the mainstream LR and CMA-ES are worse for a small number of data compared with Na{\"i}ve Bayes and AdaBoost.",

keywords = "Machine Learning, Modeling Attacks, Physical Unclonable Functions",

author = "Yue Fang and Qingqing Ma and Chongyan Gu and Chenghua Wang and Maire O'Neill and Weiqiang Liu",

year = "2019",

doi = "10.1109/APCCAS.2018.8605618",

language = "English",

pages = "394--397",

booktitle = "2018 IEEE Asia Pacific Conference on Circuits and Systems (APCCAS)",

publisher = " IEEE ",

note = "14th IEEE Asia Pacific Conference on Circuits and Systems, APCCAS 2018 ; Conference date: 26-10-2018 Through 30-10-2018",

}

Fang, Y, Ma, Q, Gu, C, Wang, C, O'Neill, M & Liu, W 2019, Attacking Arbiter PUFs Using Various Modeling Attack Algorithms: A Comparative Study. in 2018 IEEE Asia Pacific Conference on Circuits and Systems (APCCAS)., 8605618, IEEE , pp. 394-397, 14th IEEE Asia Pacific Conference on Circuits and Systems, APCCAS 2018, Chengdu, China, 26/10/2018. https://doi.org/10.1109/APCCAS.2018.8605618, https://doi.org/10.1109/APCCAS.2018.8605618

TY - GEN

T1 - Attacking Arbiter PUFs Using Various Modeling Attack Algorithms: A Comparative Study

AU - Fang, Yue

AU - Ma, Qingqing

AU - Gu, Chongyan

AU - Wang, Chenghua

AU - O'Neill, Maire

AU - Liu, Weiqiang

PY - 2019

Y1 - 2019

N2 - In this paper, we investigate the effectiveness of four different modeling attack algorithms, including Logistic Regression (LR), Naïve Bayes, AdaBoost and Covariance Matrix Adaptation Evolutionary Strategies (CMA-ES), on attacking arbiter physical unclonable functions (APUFs). A comparison of experimental results using theses algorithms is presented. The results show that the performance of the algorithms is related to the number of training data, the noise level involved in the APUF design and the number of stages in the generation of each bit response. It is found that the mainstream LR and CMA-ES are worse for a small number of data compared with Naïve Bayes and AdaBoost.

AB - In this paper, we investigate the effectiveness of four different modeling attack algorithms, including Logistic Regression (LR), Naïve Bayes, AdaBoost and Covariance Matrix Adaptation Evolutionary Strategies (CMA-ES), on attacking arbiter physical unclonable functions (APUFs). A comparison of experimental results using theses algorithms is presented. The results show that the performance of the algorithms is related to the number of training data, the noise level involved in the APUF design and the number of stages in the generation of each bit response. It is found that the mainstream LR and CMA-ES are worse for a small number of data compared with Naïve Bayes and AdaBoost.

KW - Machine Learning

KW - Modeling Attacks

KW - Physical Unclonable Functions

UR - http://www.scopus.com/inward/record.url?scp=85062219355&partnerID=8YFLogxK

U2 - 10.1109/APCCAS.2018.8605618

DO - 10.1109/APCCAS.2018.8605618

M3 - Conference contribution

AN - SCOPUS:85062219355

SP - 394

EP - 397

BT - 2018 IEEE Asia Pacific Conference on Circuits and Systems (APCCAS)

PB - IEEE

T2 - 14th IEEE Asia Pacific Conference on Circuits and Systems, APCCAS 2018

Y2 - 26 October 2018 through 30 October 2018

ER -