This paper focuses on training machine learning models using the XGBoost and extremely randomized trees algorithms on two datasets obtained using static and dynamic analysis of real malicious and benign samples. We then compare their success rates—both mutually and with other algorithms, such as the random forest, the decision tree, the support vector machine, and the naïve Bayes algorithms, which we compared in our previous work on the same datasets. The best performing classification models, using the XGBoost algorithm, achieved 91.9% detection accuracy and 98.2% sensitivity, 0.853 AUC, and 0.949 F1 score on the static analysis dataset, and 96.4% accuracy and 98.5% sensitivity, 0.940 AUC, and 0.977 F1 score on the dynamic analysis dataset. Then, we exported the best performing machine learning models and used them in our proposed MLMD program, automating the process of static and dynamic analysis and allowing the trained models to be used for classification on new samples.

The rapid deployment of technologies that can share data brings, in addition to the positive aspects, also technologies that an attacker can use to misuse personal data. Vulnerabilities in the network can be divided according to the type of attack into horizontal attacks from the perspective of the attacker and vertical attacks from the perspective of the victim. An important goal of organizations is to successfully defend against such an attack. The search for attacks on the network infrastructure can be ensured by implementing machine learning that can capture the current attack. This work describes methods of searching for attacks using graphical representation of data and also using machine learning of the high count type at different sizes of the investigated segments.

The main aim of the presented paper is to create a web portal, which allows the user to reckognize the sequence of chords in the song. To recognize chords from an audio recording, it is necessary to use input signal processing methods such as constant Q-transform or harmonic pitch class profile. A categorization template is created for each supported chord that maximizes the match between the processed signal and the chord. Techniques such as temporal and spectral smoothing or detection of harmonic changes were used for preprocessing. Based on the evaluation methods, the best classification strategy was selected, whose success prediction accuracy reaches 75 percent. Success has been achieved through the use of machine learning techniques. The system is publicly available on the public domain for anyone interested in this type of service.