Marcin Mrukowicz

This contribution proposes an ensemble classification model which is based on neural networks prediction models and well-known online incremental learning models.The considered neural network models belong to different families, namely long-short term memory, deep feed forward and convolutional neural networks. The incremental learning models considered are Passive Aggressive, Bernoulli Naive Bayes and Stochastic Gradient Descent Classifiers. This paper aims to develop a prediction model that reduces false positives (FP) while maintaining overall model performance. Moreover, the stability of the model over time and its ability to correctly classify phishing links, even if the concept shift occur, are under considerations. The ensemble model shows promising results, demonstrating its superiority over base models. Some proposed models significantly outperform some base models according to statistical tests.

This contribution proposes a classifier designed to reduce the number of false positive detections. It is a self-tuning model, tested in the context of phishing link detection. In this prediction model diverse types of aggregation functions and time-series data periods are used. Aggregation functions are employed to integrate the prediction values of classification models applied in the email phishing problem. Dividing a dataset into subsets allows for incremental learning strategies. This makes it possible to gradually improve the model by using previously acquired knowledge when training on new data. The aim of the contribution is to discuss the problem of obtaining minimal value of FPR while simultaneously getting maximal value of TPR. We applied the proposed ensemble model and neural networks models which were adjusted to the incremental learning strategy (and as base models were applied typical examples of incremental learning models). The study analyzes the dataset provided by FreshMail company. The reason to consider this problem arose with the real-life problem of the Freshamil Company and the data provided by this Company. This dataset uniquely fulfills the criteria essential for our experiments. Unlike other phishing datasets, this data provides dates which is important for the incremental learning approach. The proposed approach of ensemble learning models, based on aggregation functions, is compared to the well-known neural network models which may be treated as state of the art models in recognizing phishing attacks. The main advantage of the proposed algorithm is achieving high numbers of true positives while simultaneously achieving relatively small number of false positives. According to the statistical tests, for some of the desired TPR levels, the proposed model obtained significantly better by a few percentage points results than neural network models. It mitigates the cost arising from the manual analysis of these cases by domain experts.

The purpose of the study is to propose a multi-class ensemble classifier using interval modeling dedicated to microarray datasets. An approach of creating the uncertainty intervals for the single prediction values of constituent classifiers and then aggregating the obtained intervals with the use of interval-valued aggregation functions is used. The proposed heterogeneous classification employs Random Forest, Support Vector Machines, and Multilayer Perceptron as component classifiers, utilizing cross-entropy to select the optimal classifier. Moreover, orders for intervals are applied to determine the decision class of an object. The applied interval-valued aggregation functions are tested in terms of optimizing the performance of the considered ensemble classifier. The proposed model’s quality, superior to other well-known and component classifiers, is validated through comparison, demonstrating the efficacy of cross-entropy in ensemble model construction.

In this contribution methods for improving the quality of multi-class classification by the k nearest neighborhood classifiers in the case of large number of missing values in data sets are considered. Two versions of classifiers are compared. In the first case the aggregation of certainty coefficients of the individual classifiers with the use of the arithmetic mean is applied. In the second case interval modelling and interval-valued aggregation functions are involved. It is proved that the classifier which uses interval methods entails a much slower decrease in classification quality.