Комбинированная методика проектирования защищенных встроенных устройств на примере системы охраны периметра

This paper aims to test the hypothesis that the quality of social media bot detection systems based on supervised machine learning may not be as accurate as researchers claim, given that bots have become increasingly sophisticated, making it difficult for human annotators to detect them better than random selection. As a result, obtaining a ground-truth dataset with human annotation is not possible, which leads to supervised machine-learning models inheriting annotation errors. To test this hypothesis, we conducted an experiment where humans were tasked with recognizing malicious bots on the VKontakte social network. We then compared the “human” answers with the “ground-truth” bot labels (‘a bot’/‘not a bot’). Based on the experiment, we evaluated the bot detection efficiency of annotators in three scenarios typical for cybersecurity but differing in their detection difficulty as follows: (1) detection among random accounts, (2) detection among accounts of a social network ‘community’, and (3) detection among verified accounts. The study showed that humans could only detect simple bots in all three scenarios but could not detect more sophisticated ones (p-value = 0.05). The study also evaluates the limits of hypothetical and existing bot detection systems that leverage non-expert-labelled datasets as follows: the balanced accuracy of such systems can drop to 0.5 and lower, depending on bot complexity and detection scenario. The paper also describes the experiment design, collected datasets, statistical evaluation, and machine learning accuracy measures applied to support the results. In the discussion, we raise the question of using human labelling in bot detection systems and its potential cybersecurity issues. We also provide open access to the datasets used, experiment results, and software code for evaluating statistical and machine learning accuracy metrics used in this paper on GitHub.

Обзор методологических примитивов для поэтапного построения модели визуализации данных

Currently, the methods and means of human–machine interaction and visualization as its integral part are being increasingly developed. In various fields of scientific knowledge and technology, there is a need to find and select the most effective visualization models for various types of data, as well as to develop automation tools for the process of choosing the best visualization model for a specific case. There are many data visualization tools in various application fields, but at the same time, the main difficulty lies in presenting data of an interconnected (node-link) structure, i.e., networks. Typically, a lot of software means use graphs as the most straightforward and versatile models. To facilitate visual analysis, researchers are developing ways to arrange graph elements to make comparing, searching, and navigating data easier. However, in addition to graphs, there are many other visualization models that are less versatile but have the potential to expand the capabilities of the analyst and provide alternative solutions. In this work, we collected a variety of visualization models, which we call alternative models, to demonstrate how different concepts of information representation can be realized. We believe that adapting these models to improve the means of human–machine interaction will help analysts make significant progress in solving the problems researchers face when working with graphs.