A Novel Modeling-Attack Resilient Arbiter-PUF Design

Ebrahimabadi, Mohammad; Younis, Mohamed; Lalouani, Wassila; Karimi, Naghmeh

doi:10.1109/vlsid51830.2021.00026

Cited by 10 publications

(9 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ebrahimabadi et al [25] showed that the latter bits of the APUF challenge had a higher impact on determining the response (i.e., to be '1'/'0') than former challenge bits. Specifically, the Most Significant Bit (MSB), c[n − 1], is the most influential challenge bit on the response of an APUF.…”

Section: N S1s2s3 Arbiter-pufmentioning

confidence: 99%

“…Based on the above observation, they proposed an APUF variant to increase its modeling resilience, termed as M n S1,S2,S3 -APUF, which consists of one main APUF and Fig. 4: M n S1,S2,S3 -APUF [25] three auxiliary APUFs. The n represents the stage of the main APUF, S 1 , S 2 and S 3 denote the number of stages (i.e.…”

Section: N S1s2s3 Arbiter-pufmentioning

confidence: 99%

“…size for simplicity) of the auxiliary APUFs that drive the first, second, and third most significant bit of the main APUF's challenge, respectively. Note that when the size of auxiliary APUFs is less than n bits, they are fed with a subset of the n-bit challenge of the main APUF [25].…”

Section: N S1s2s3 Arbiter-pufmentioning

confidence: 99%

“…Because both of them utilize auxiliary APUFs to generate the obfuscated challenge bit(s). Here for the M n S1,S2,S3 -APUF, the main APUF has 64 stages, while the three auxiliary APUFs are with 32, 16, and 8 stages, respectively, following the same original setting in [25]. For the (x, y)-iPUFs, several configurations are evaluated.…”

Section: N S1s2s3 -Apuf and (X Y)-ipufsmentioning

confidence: 99%

“…The FF-APUF responses can also be XORed to form XOR-FF-APUFs. Recently, there are designs leveraging standalone auxiliary APUF's response(s) to act as obfuscated challenge bit(s), which include the iPUF [24] and M n S1,S2,S3 -APUF [25] (both designs are detailed in Section 3). These challenge obfuscated APUFs (termed as CO-APUFs) exhibit greatly enhanced modeling resilience to conventional modeling attacks such as logistic regression (LR), and CMA-ES.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Systematically Evaluation of Challenge Obfuscated APUFs

Gao¹,

Yao²,

Pang³

et al. 2022

Preprint

View full text Add to dashboard Cite

As a well-known physical unclonable function that can provide huge number of challenge response pairs (CRP) with a compact design and fully compatibility with current electronic fabrication process, the arbiter PUF (APUF) has attracted great attention. To improve its resilience against modeling attacks, many APUF variants have been proposed so far. Though the modeling resilience of response obfuscated APUF variants such as XOR-APUF and lightweight secure APUF (LSPUF) have been well studied, the challenge obfuscated APUFs (CO-APUFs) such as feed-forward APUF (FF-APUF), and XOR-FF-APUF are less elucidated, especially, with the deep learning (DL) methods. This work systematically evaluates five CO-APUFs including three influential designs of FF-APUF, XOR-FF-APUF, iPUF, one very recently design (dubbed as M n S 1 ,S 2 ,S 3 -APUF) and our newly optimized design (dubbed as OAX-FF-APUF), in terms of their reliability, uniformity (related to uniqueness), and modeling resilience. Three DL techniques of GRU, TCN and MLP are employed to examine these CO-APUFs' modeling resilience-the first two are newly explored. With computation resource of a common personal computer, we show that all five CO-APUFs with relatively large scale can be successfully modeled-attacking accuracy higher or close to its reliability. The hyper-parameter tuning of DL technique is crucial for implementing efficient attacks. Increasing the scale of the CO-APUF is validated to be able to improve the resilience but should be done with minimizing the reliability degradation. As the powerful capability of DL technique affirmed by us, we recommend the DL, specifically the MLP technique always demonstrating best efficacy, to be always considered for examining the modeling resilience when newly composited APUFs are devised or to a large extent, other strong PUFs are constructed.

show abstract

Section: N S1s2s3 Arbiter-pufmentioning

confidence: 99%

Section: N S1s2s3 Arbiter-pufmentioning

confidence: 99%

Section: N S1s2s3 Arbiter-pufmentioning

confidence: 99%

Section: N S1s2s3 -Apuf and (X Y)-ipufsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations