A practical DPA on Grain v1 using LS-SVM

In this paper, we demonstrate a new Differential Power Analysis (DPA) attack technique against Grain v1 stream cipher by resynchronizing the cipher multiple times with the same value of the secret key and different initialization vectors (IVs). Our proposed attack strategy requires less than a hundred randomly generated IVs (expected value) to retrieve the whole 80-bit key. Further, the power trace classifications of Grain v1 cipher implemented on SASEBO G-II standard side channel evaluation board is shown in order to validate our proposed DPA attack against the cipher. The captured power traces were analyzed using Least Squares Support Vector Machine (LS-SVM) learning algorithm based multiclass classifiers to classify the power traces into the respective Hamming distance (HD) classes. To extract power samples with high information about HD classes, Signal-to-noise ratio (SNR) metric was chosen for feature selection. The experiment of power trace classifications of test set showed a high success rate of 98% when the five largest SNR sample instants over a clock cycle were chosen as features.