TY - JOUR
T1 - A fast deep learning method for security vulnerability study of XOR PUFs
AU - Mursi, Khalid T.
AU - Thapaliya, Bipana
AU - Zhuang, Yu
AU - Aseeri, Ahmad O.
AU - Alkatheiri, Mohammed Saeed
N1 - Publisher Copyright:
© 2020 by the authors. Licensee MDPI, Basel, Switzerland.
PY - 2020/10
Y1 - 2020/10
N2 - Physical unclonable functions (PUF) are emerging as a promising alternative to traditional cryptographic protocols for IoT authentication. XOR Arbiter PUFs (XPUFs), a group of well-studied PUFs, are found to be secure against machine learning (ML) attacks if the XOR gate is large enough, as both the number of CRPs and the computational time required for modeling n-XPUF increases fast with respect to n, the number of component arbiter PUFs. In this paper, we present a neural network-based method that can successfully attack XPUFs with significantly fewer CRPs and shorter learning time when compared with existing ML attack methods. Specifically, the experimental study in this paper shows that our new method can break the 64-bit 9-XPUF within ten minutes of learning time for all of the tested samples and runs, with magnitudes faster than the fastest existing ML attack method, which takes over 1.5 days of parallel computing time on 16 cores.
AB - Physical unclonable functions (PUF) are emerging as a promising alternative to traditional cryptographic protocols for IoT authentication. XOR Arbiter PUFs (XPUFs), a group of well-studied PUFs, are found to be secure against machine learning (ML) attacks if the XOR gate is large enough, as both the number of CRPs and the computational time required for modeling n-XPUF increases fast with respect to n, the number of component arbiter PUFs. In this paper, we present a neural network-based method that can successfully attack XPUFs with significantly fewer CRPs and shorter learning time when compared with existing ML attack methods. Specifically, the experimental study in this paper shows that our new method can break the 64-bit 9-XPUF within ten minutes of learning time for all of the tested samples and runs, with magnitudes faster than the fastest existing ML attack method, which takes over 1.5 days of parallel computing time on 16 cores.
KW - FPGA
KW - IoT security
KW - Machine-learning
KW - Resource-constrained IoT
KW - XOR PUF
UR - http://www.scopus.com/inward/record.url?scp=85092708589&partnerID=8YFLogxK
U2 - 10.3390/electronics9101715
DO - 10.3390/electronics9101715
M3 - Article
AN - SCOPUS:85092708589
SN - 2079-9292
VL - 9
SP - 1
EP - 13
JO - Electronics (Switzerland)
JF - Electronics (Switzerland)
IS - 10
M1 - 1715
ER -