Many researches transform the traditional side channel analysis (SCA) into a classification problem. However, there are some inconsistencies in the evaluation metrics and excessive training overhead. A regression model theory is proposed from power traces to intermediate values in this work. It leads us to design a random convolution model that can closely fit the timing features of power consumption and transform them directly to intermediate values. In training phase, the raw power traces on ASCAD is processed to the dataset with six subsets, which is similar to the form of UCR sets. The det...