TY - GEN
T1 - Neural Networks for Authenticating Integrated Circuits Based on Intrinsic Nonlinearity
AU - Sadasivuni, Sudarsan
AU - Chandrasekaran, Sanjeev Tannirkulam
AU - Jayaraj, Akshay
AU - Sanyal, Arindam
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/8
Y1 - 2020/8
N2 - This work presents a machine learning approach to identify integrated circuits based on intrinsic nonlinearity arising out of random variations introduced during device fabrication. The random variations ensure that each integrated circuit has a distinct nonlinearity signature which can be analyzed by a machine learning model to distinguish between chips fabricated from the same mask. We have analyzed multiple samples of two analog-to-digital converters (ADCs) - a continuous-time ?S oversampled ADC and a discrete-time nyquist ADC. The two ADCs have different dominant nonlinearity contributors - inter-symbol interference for the oversampled ADC and static mismatch for the nyquist ADC. A 3-layer artificial neural network can identify the different sample chips for each ADC with a worst-case mean accuracy of 95.97%.
AB - This work presents a machine learning approach to identify integrated circuits based on intrinsic nonlinearity arising out of random variations introduced during device fabrication. The random variations ensure that each integrated circuit has a distinct nonlinearity signature which can be analyzed by a machine learning model to distinguish between chips fabricated from the same mask. We have analyzed multiple samples of two analog-to-digital converters (ADCs) - a continuous-time ?S oversampled ADC and a discrete-time nyquist ADC. The two ADCs have different dominant nonlinearity contributors - inter-symbol interference for the oversampled ADC and static mismatch for the nyquist ADC. A 3-layer artificial neural network can identify the different sample chips for each ADC with a worst-case mean accuracy of 95.97%.
UR - http://www.scopus.com/inward/record.url?scp=85090561961&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85090561961&partnerID=8YFLogxK
U2 - 10.1109/MWSCAS48704.2020.9184655
DO - 10.1109/MWSCAS48704.2020.9184655
M3 - Conference contribution
AN - SCOPUS:85090561961
T3 - Midwest Symposium on Circuits and Systems
SP - 253
EP - 256
BT - 2020 IEEE 63rd International Midwest Symposium on Circuits and Systems, MWSCAS 2020 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 63rd IEEE International Midwest Symposium on Circuits and Systems, MWSCAS 2020
Y2 - 9 August 2020 through 12 August 2020
ER -