Current Mirror Array: A Novel Circuit Topology for Combining Physical Unclonable Function and Machine Learning

Wang, Zheng; Chen, Yi; Patil, Aakash; Jayabalan, J.; Zhang, Xueyong; Chang, Chip-Hong; Basu, Arindam

doi:10.1109/tcsi.2017.2743004

Cited by 48 publications

(27 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Reliability is defined as the probability of 1-bit output being correct across different operating conditions such as temperature/voltage/time etc. As shown in [8], we also observed that reliability variation with temperature is far more dominant than other effects. So we will use this worst-case reliability at −45 • C for our analysis going forward.…”

Section: Conventional Nn-puf Reliabilitysupporting

confidence: 69%

“…The row challenge bits selects which row of transistors are active. The current values for each column of the column pair are summed up, and the two results are sent to the comparator to generate 1(I C col,A > I C col,B ) or 0(I C col,A < I C col,B ) where I C col,A denotes the current output for column A given a challenge C. The only difference is we show a shared comparator while [8] used current controlled oscillators (CCO) to digitize the current values. We note that the maximum number of possible column pairs is n col 2 where n col is the number of columns.…”

Section: The Conventional Nn-pufmentioning

confidence: 99%

“…In order to improve reliability of the NN-PUF, it was shown in [8] that we can use a dynamic threshold control, V ctrl , but it comes at the cost of discarding more CRPs. In that scheme, a response is considered valid if and only if |I C col,X − I C col,Y | > V ctrl .…”

Section: Conventional Nn-puf Reliabilitymentioning

confidence: 99%

“…Another problem with conventional PUFs such as that shown in [6,8] is the low Hamming Distance Test [13] value of the output due to the comparator's bias, which biases the output toward 0 or 1, and makes it easier to predict the response. For the NN-PUF in [8], this can be modeled as a gain factor k X multiplying the output current I C col,X of the X-th column.…”

Section: Conventional Nn-puf ML Attack Accuracymentioning

confidence: 99%

“…In order to improve over a conventional PUF's attack susceptibility, we propose the design of an RNN-PUF, whose concept is shown in Figure 4(a). Feed-forward Neural networks such as Extreme Learning Machine have been implemented in hardware before [8] and used in dual-mode as a PUF. Our hypothesis was if we use the idea of Recurrent Neural Networks for a PUF, it may improve resistance to Machine Learning attacks by introducing non-linearity in the CRP space through the feedback mechanism.…”

Section: Proposed Rnn-pufmentioning

confidence: 99%

See 4 more Smart Citations

A 0.16pJ/bit recurrent neural network based PUF for enhanced machine learning attack resistance

Shah

Alam

Sahoo

et al. 2019

Proceedings of the 24th Asia and South Pacific Design Automation Conference

Self Cite

View full text Add to dashboard Cite

Physically Unclonable Function (PUF) circuits are finding widespread use due to increasing adoption of IoT devices. However, the existing strong PUFs such as Arbiter PUFs (APUF) and its compositions are susceptible to machine learning (ML) attacks because the challenge-response pairs have a linear relationship. In this paper, we present a Recurrent-Neural-Network PUF (RNN-PUF) which uses a combination of feedback and XOR function to significantly improve resistance to ML attack, without significant reduction in the reliability. ML attack is also partly reduced by using a shared comparator with offset-cancellation to remove bias and save power. From simulation results, we obtain ML attack accuracy of 62% for different ML algorithms, while reliability stays above 93%. This represents a 33.5% improvement in our Figure-of-Merit. Power consumption is estimated to be 12.3µW with energy/bit of ≈ 0.16pJ.

show abstract

Section: Conventional Nn-puf Reliabilitysupporting

confidence: 69%

Section: The Conventional Nn-pufmentioning

confidence: 99%

Section: Conventional Nn-puf Reliabilitymentioning

confidence: 99%