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.

As the IoT industry strongly extends there is a need for better security and threat detection tools. Many approaches are possible but the tendency is to detect attacks externally by using network traffic analysis. Network based intrusion detection could lead to satisfactory results however it is uncertain if host based methods would not give better results as IoT devices usually have repeatable and predictable behavior. Unfortunately host based detection methods can neither be directly compared against each other nor be compared to network based systems as there are no publicly available data sets with IoT device operating system traces. In this paper we propose and describe a framework which allows for emulation of IoT devices, simulation of random attacks and gathering of the operating system traces for Linux based IoT devices. We also publish the first gathered data set and we plan to release new extended data sets in near future.

The fashion industry is characterised by the need to make demand forecasts in advance and for highly volatile products for which we often have no sales history at the time the forecasts are made.For this reason, it is necessary to propose forecast mechanisms that can cope with the given conditions.Such forecasts can be based on expert predictions for generalized product categories.In this case, the task of machine learning forecasting methods would be to divide the aggregate prediction into forecasts for individual products, in each colour and size.In the paper, we present several approaches to this specific task.We present the use of the naive method, custom nearest neighbour approach, parametric linear mixed model and an ensemble approach.Overall, the best results we obtained for the ensemble method.Our research was based on real data from fashion retail.

Assuring the network traffic safety is a very important issue in a variety of today’s industries. Therefore, the development of anomalies and attacks detection methods has been the goal of analyses. In the paper the binary classification-based approach to network traffic safety monitoring is presented. The well known methods were applied to artificially modified network traffic data and their detection capabilities were tested. More detailed interpretation of the nature of detected anomalies is carried out with the help of the XAI approach. For the purpose of experiments a new benchmark network traffic data set was prepared, which is now commonly available.