Predicting Soft-Response of MUX PUFs via Logistic Regression of Total Delay Difference
Anoop Koyily, Chen Zhou, Chris H. Kim, Keshab K. Parhi · 2018
This paper presents a logistic regression based approach to predict the soft-response for a challenge using the total delay-difference as an input. This approach enables us to determine whether a challenge is stable or not. Soft-response is the probability of response bit corresponding to the challenge being 1. The total delay-difference is computed from the input challenge by assuming that the delay-difference of the stages are known. The approach learns a logistic function based on the total delay-difference which has just 3 parameters. Therefore, this is a simple approach which gives comparable performance against a more complex approach based on artificial neural network (ANN) models. The model demonstrates good sensitivity and precision but poor specificity. Furthermore, we use scaling parameter of the logistic function to study its relation to the arbiter's timing parameters like setup and hold time.