A set of manipulated and unmanipulated pairwise comparison matrices

A distinct set of the training data was generated for each of the tested size of the PC matrix C. Each set consists of three distinct *.json files, which are used to train and test the neural networks designed to detect one of the three described attack algorithms (naive, basic, advanced). The previously mentioned *.json files have the same name as the algorithm they are used to test (e.g. basic.json), and are placed in a folder whose name determines the size (n) of the matrix C and the number of independent data samples for each of the tested algorithms (e.g. data_7_7_10000). Each of the data sample is structured as follows: • id - index of the sample • CI - Saaty's consistency ratio of PC matrix C • matrix - generated PC matrix C • errorMatrix - error matrix calculated for matrix • koczkodajInconsistencyMatrix - modified Koczkodaj's inconsistency matrix calculated for matrix • determinantMatrix - determinant matrix (12) calculated for matrix • distrurbedCI - Saaty's consistency ratio of modified PC matrix C' • distrurbedMatrix - modified (because of the carried out attack) PC matrix C' • distrurbedErrorMatrix - determinant matrix (12) calculated for disturbedMatrix • distrurbedKoczkodajInconsistencyMatrix - modified Koczkodaj's inconsistency matrix calculated for disturbedMatrix • distrurbedDeterminantMatrix - Analogously to determinantMatrix, but calculated for disturbedMatrix Some of that fields are not used in the experiments (e.g. koczkodajInconsistencyMatrix) but we think that they may prove useful in future studies.