Horizontal SCA Attacks against $kP$ Algorithm Using K-Means and PCA

Abstract

Side Channel Analysis attacks take advantage of the information leaked from the implementations of cryptographic algorithms. In this paper we describe two key revealing methods which are based on machine learning algorithms: K-means and PCA. We performed the attacks against ECDSA implementations without any prior knowledge about the key and achieved 100% accuracy for an implementation without any countermeasures against horizontal attacks and 88.7% accuracy for an implementation with bus address sequencing. In the scenario where the kP operation inputs are controlled by the attacker (as during signature verification), we achieved 98.3% accuracy for the implementation with countermeasures.

A modified LSTM neural network model for stock price prediction based on auxiliary information and model average

“…In particular, for intraday price data, dimension reduction extraction is required during processing. Common dimension reduction methods include principal component analysis (PCA) (Aftowicz [8]), kernel principal component analysis (KPCA) (Lu2022 [9]). However, these dimension reduction methods are only applicable to multivariate data analysis and are not applicable to time series data, In consideration of the high correlation between the observation time points of the time series data and the time series can be regarded as a discrete realization of the random process, we can use B-spline basis function, Fourier basis function, Gaussian basis function, functional principal component analysis (Jarry2022 [10]) and other basis function smoothing methods to extract the functional features of the intraday price data while reducing the dimension.…”