This paper describes security indicators specific to digital manufacturing. We divided the set of indicators into three groups: self-similarity-based security indicators, sustainability indicators, and indicators characterizing the homeostatic ability of cyberphysical systems that form the basis of digital production. Indicators can be applied to any type of digital production systems to detect security problems, control the sustainability of their operation, and maintain resilience.

Digital Manufacturing Security Indicators

This paper provides an approach to the detection of information security breaches in automated process control systems (APCS), which consists in forecasting multivariate time series formed from the values of the operating parameters of the end system devices. Using an experimental model of water treatment, a comparison was made of the forecasting results for the parameters characterizing the operation of the entire model, and for the parameters characterizing the flow of individual subprocesses implemented by the model. For forecasting, GRU-neural network training was performed.

Using GRU neural network for cyber-attack detection in automated process control systems

Kalman filter is an efficient data processing algorithm that removes noise and unnecessary information, and also performs system state prediction. This paper proposes the use of a Kalman filter to solve the problem of forecasting time series describing the gasoil heating loop process. The limitations associated with this approach are described, as well as the advantages compared to other predictive models.

Predicting cyber attacks on industrial systems using the Kalman filter

This article explores the use of deep learning for malware identification in the Android operating system. Similar studies are considered and, based on their drawbacks, a self-designed approach is proposed for representing an Android application for a convolutional neural network, which consists in constructing an RGB image, the pixels of which are formed from a sequence of pairs of API calls and protection levels. The results of the experimental evaluation of the proposed approach, which are presented in this paper, demonstrate its high efficiency for solving the problem of identifying malicious Android applications.

Applying deep learning techniques for Android malware detection

The Arctic zone of Russia has an area of more than 9 million square kilometers (4.9 million sq. km continental part, 4.0 million sq. km—sea, 0.2 sq. km—islands). The land areas of the Arctic zone of the Russian Federation include the Nenets, Yamalo-Nenets, Chukotka Autonomous Districts (hereinafter—AD), the Murmansk Region and most of the municipal entities of the Arkhangelsk Region, as well as coastal municipalities of the Krasnoyarsk Territory, the Komi Republic and the Sakha Republic (Yakutia). About 2.5 million people live here (less than 2% of the country’s population, but about 40% of the population of the entire Arctic). Almost 15% of Russia’s gross domestic product (hereinafter referred to as GDP) is produced here. About 1/5 of Russian exports are being created in the Russian Arctic. The continental shelf of the Arctic Ocean contains approximately 25% of the world’s shelf reserves of hydrocarbons. According to the US Geological Survey of 2008, up to 134 billion barrels of oil (about 18 billion tons) and almost 47 trillion m3 of natural gas may be deposited in the northern regions. In 2017, the Russian Arctic accounted for up to 60% of all-Russian copper and oil production, almost 100% of natural gas, 100% of diamonds, barite, platinum, nickel, cobalt, rare earth elements, vermiculite, and apatite concentrate. However, to increase the potential of the land Arctic territories of Russia, it is necessary to implement large-scale projects for the extraction, processing and supply of hydrocarbon fuels, the development of energy and transport infrastructure, the formation of an innovative economy based on high technologies. This experience allows us to obtain new knowledge of the mechanisms for regional development of the Arctic territories, as well as to take into account the accumulated foreign experience in developing the decisions in the field of regional Arctic policy. A comparative analysis of the territories of foreign countries that are in comparable natural-geographical, socio-economic, geopolitical conditions, but differing in the level of economic development and social attractiveness, has been done the basis of identifying the main directions of development of the Arctic regions of the Russian Federation, defined in federal and regional strategic documents. The use of this experience of territorial development may be useful for the Russian Arctic regions.

Methodological aspects of use of countries experience in determining the directions of the strategic development of the Russian Federation arctic regions

A method for detecting anomalies in the work of cyberphysical systems by analyzing a multidimensional time series is proposed. The method is based on the use of neural network technologies to predict the values ​​of the time series of the system data and to identify deviations between the predicted value and the current data obtained from the sensors and actuators. The results of experimental studies are presented, which testify to the effectiveness of the proposed solution.

Detection of Threats in Cyberphysical Systems Based on Deep Learning Methods Using Multidimensional Time Series

This paper proposes a hierarchical approach to analyzing information security in modern information systems that consists of multilevel collection, analysis, and control of events. We have analyzed the mechanisms and peculiarities of how malware acts at each level of the information system, determined the features of the mechanisms of action of malware, its masking, and possible methods for detecting malware.

Hierarchical approach to analyzing security breaches in information systems

The specifics of secure interaction in large-scale industrial systems is investigated, the requirements for group authentication schemes are determined allowing for the specifics. The analysis of approaches to the organization of secure interaction between system nodes based on the group authentication is carried out. The prospects for the application of group authentication in large-scale industrial systems are considered.

Analysis of Approaches to Group Authentication in Large-Scale Industrial Systems

This paper presents the results from developing the system for detecting malicious Android applications based on the fuzzy clustering method. We have described the format of the application feature vector, as well as presented studies on the effectiveness of using different criteria for separability. The high efficiency of the proposed approach has been experimentally confirmed.

Application of clustering methods for analyzing the security of Android applications

Cryptographic access control is a relatively new concept that implements the access control rules of some subjects to an object using cryptographic primitives. A quantum computer of sufficient capacity allows solving in polynomial time the discrete logarithm and integer factorization problems, which are the basis of most modern public-key cryptosystems. In this regard, there is a need to search for new problems that are resistant to attacks on both classical computers and quantum computers. Computing the isogenies of supersingular elliptic curves is one of the most challenging problems. A scheme for cryptographic access control based on isogenies is proposed. Security analysis of the protocol and the results of practical implementation in the SAGE computer algebra system are given.

A. V. Yarmak

Papers

Detection of Threats in Cyberphysical Systems Based on Deep Learning Methods Using Multidimensional Time Series

Hierarchical approach to analyzing security breaches in information systems

Analysis of Approaches to Group Authentication in Large-Scale Industrial Systems

Application of clustering methods for analyzing the security of Android applications

Isogeny-Based Cryptographic Access Control