The paper presents a novel approach to investigating adversarial attacks on machine learning classification models operating on tabular data.The employed method involves using diagnostic parameters calculated on an approximated representation of a model under attack and analyzing differences in these diagnostic parameters over time.The hypothesis researched by the authors is that adversarial attack techniques, even if attempting a low-profile modification of input data, influence those diagnostic attributes in a statistically significant way.Thus, changes in diagnostic attributes can be used for detecting attack events.Three attack approaches on real-world datasets were investigated.The experiments confirm the approach as a promising technique to be further developed for detecting adversarial attacks.

The paper discusses a data science competition centered around the development of an anomaly detection system for IoT devices.The competition utilized a unique environment that allowed for the operation and monitoring of real IoT devices, including scheduling of attacks on these devices.The environment was used to collect the data, which included both normal and attack-induced behavior of IoT devices.The paper presents the background of the competition, the top models submitted, and the competition results.The paper also includes a discussion about restrictions related to the use of synthetic attack data as input for constructing anomaly detection systems.

We describe the 7th edition of the international data mining competition held at Knowledge Pit in association with the FedCSIS conference series.The goal was to predict workloadrelated characteristics of monitored network devices.We analyze solutions uploaded by the most successful participants.We investigate prediction errors which had the greatest influence on their results.We also present our own baseline solution which turned out to be the most reliable in the final evaluation.

We consider a problem of learning from compact representations of images for a purpose of object recognition and content-based image retrieval. We discuss a motivation for using compressed images in those tasks and indicate exemplary applications related to analysis on the data from satellites. Finally, we show some preliminary results of experiments conducted to demonstrate the impact of the image data granulation on the quality of classification. We empirically compare the performance of prediction models trained on original images, images compressed using autoencoders, and on images whose quality was lowered in order to reduce their size.