gianghp/ViginereCipher_features

这个数据集是基于论文《An Artificial Neural Network Approach to Finding the Key Length of the Vigenère Cipher》构建的，旨在支持训练神经网络以预测使用Vigenère密码加密的文本的密钥长度。数据集由多个文本文件经过预处理和加密得到，包含77个基于原始论文方法提取的特征。这些特征包括文本长度、重复序列计数、重合指数、基于扭曲的特征、平均重合指数等。数据集适用于训练机器学习模型预测Vigenère密码的密钥长度以及评估结合传统方法和深度学习的密码分析技术。

This dataset is based on the paper An Artificial Neural Network Approach to Finding the Key Length of the Vigenère Cipher and is designed to support training neural networks for predicting the key length of text encrypted with the Vigenère cipher. The dataset consists of multiple text files that have been preprocessed and encrypted, containing 77 features extracted using methods from the original paper. These features include text length, repeated sequence count, index of coincidence, twist-based features, average index of coincidence for cosets, etc. The dataset is suitable for training machine learning models to predict the key length of the Vigenère cipher and for evaluating cryptographic analysis techniques that combine classical methods with deep learning.