Improving Differential Power Analysis By Elastic Alignment

To prevent smart card attacks using Differential Power Analysis (DPA), manufacturers commonly implement DPA countermeasures that create misalignment in power trace sets and decrease the effectiveness of DPA. We design and investigate the elastic alignment algorithm for non-linearly warping trace sets in order to align them. Elastic alignment uses FastDTW, originally a method for aligning speech utterances in speech recognition systems, to obtain so-called warp paths that can be used to perform alignment. We show on traces obtained from a smart card with random process interrupts that misalignment is reduced significantly, and that even under an unstable clock the algorithm is able to perform alignment.