Showing papers presented at "International Symposium on Theoretical Aspects of Computer Software in 2020"

Algebraic immunity of vectorial boolean functions and boolean groebner bases

Abstract: The basic concepts and results related to the Boolean Groebner bases and their application for computing the algebraic immunity of vectorial Boolean functions are considered. This parameter plays an important role for the security evaluation of block ciphers against algebraic attacks. Unlike the available works, the description is carried out at the elementary level using terms of Boolean functions theory. In addition, obtained proofs are shorter than the previous ones. This allows us to achieve significant progress in building the fundamentals of the theory (for the Boolean case) using only elementary methods.The paper can be useful for students and postgraduate students studying cryptology. It may also save time for professionals who want to get familiar with the mathematical techniques used in algebraic attacks on block ciphers.

Machine learning based network traffic classification approach for Internet of Things devices

Abstract: Due to design flaws, problems with implementations and improper network configuration, the Internet of Things devices become vulnerable in the network. They can be easily compromised and can also be attached to the Botnet network. IoT devices classification allows for strengthening of the overall network security through better VLAN planning and better firewall rule fine-tuning (e.g. per device class). In this paper only two classes of devices are considered: single-purpose devices (such as a bulb) and multi-purpose devices (such as mobile phone). Existing solutions do not provide the required accuracy within the given timeframe. We propose ML-based classification method based on supervised machine learning technology (Random Forest). With advanced packets flow analysis, our proposed approach demonstrates 94% of accuracy (7% better than the existing prior art). Additionally a very low False Positive rate is guaranteed for single-purpose IoT devices (e.g. a bulb must never be classified as a multi-purpose device).

DeeDP: vulnerability detection and patching based on deep learning

Abstract: We present the DeeDP system for automatic vulnerabilities detection and patch providing. DeeDP allows to detect vulnerabilities in C/C++ source code and generate patch for fixing detected issue. This system uses deep learning methods to organize rules for deciding whether a code fragment is vulnerable. Patch generation processes can be performed based on neural network and rule-based approaches. The system uses the abstract syntax tree (AST) representations of the source code fragments. We have tested effectiveness of our approach on different open source projects. For example, Microsoft/Terminal (https://github.com/microsoft/Terminal) was analyzed with DeeDP: our system detected security issue and generated patch which was successfully approved and applied by Microsoft maintainers.

Features of Ensuring Cybersecurity of the Critical Infrastructure of the State

Abstract: One of the most important tasks of national security in modern conditions is to ensure the security and stable functioning of critical infrastructure of the state. Control systems are an integral and most vulnerable part of critical infrastructure facilities. This determines the importance of ensuring they are protected from destructive cyber actions. Destructive cyber actions in it is accompanied, as a rule, by chain effects and synergistic effects that systematically influence and cover all other spheres of the life of society and the state, both in ordinary and, especially, in critical conditions. The authors systematically and comprehensively analyzed and presented in the article the results of investigations of the features of destructive cyber actions in the critical infrastructure of state, counteracting them and protecting from them.

Methods and Techniques of Assessment of the Value Orientations of Social Media Users

Abstract: The purpose of the work is to investigate and review the general concept of sentiment analysis and the use of such approach in assessment of the value orientations of social media users. The article analyzes main components and steps of sentiment analysis and different methods and techniques which are applied at each stage. The paper also researches machine learning approach in sentiment analysis: different algorithms were reviewed in details. Authors use methods of analysis for research of technologies and means of sentiment analysis, its functions, opportunities and advantages of use; comparison methods for researching individual techniques and methods. The article states that there are many options for further improvements in sentiment analysis and authors propose an original approach for determining emotional component in text.

Comparison of Efficiency of Statistical Models Used for Formation of Feature Vectors by JPEG Images Steganalysis

Abstract: In order to build effective analytical systems for digital covers steganalysis in the given practical conditions, it is necessary to analyze and evaluate the quality of existing methods and components. Thus, it is necessary to compare the baseline characteristics of the available candidates in order to select the optimal components of the system. However, the usage of results from open scientific publications may lead to incorrect comparison due to differences in the conditions of numerical experiments. This study is based on the principle of checking the performance of statistical models for feature vectors formation under the same conditions. The case of JPEG images steganalysis with the usage of machine learning techniques is considered. The performance and detection accuracy of statistical models such as CHEN, CC-CHEN, LIU, CC-PEV, CC-C300, GFR, and DCTR in case of message hiding in the frequency domain of digital images are analyzed. The results of the study are numerical estimates of the performance and accuracy of SVM classification in binary and multilevel steganalysis modes.

Detection and correction of database schema integrity violation based on initialization scripts

Abstract: We present a new methodology for detecting and correcting database schema integrity violations. This technique uses initialization scripts, their pre-processing to compare with the current database schema. The result of the work is a prototype of the software product.

Malicious and benign websites classification using machine learning methods

Abstract: Nowadays web surfing is an integral part of the life of the average person and everyone would like to protect his own data from thieves and malicious web pages. Therefore, this paper proposes a solution to the discrimination of malicious and benign websites problem with desirable accuracy. We propose to utilize machine learning methods for classification malicious and benign websites based on URL and other host-based features. State-of-the-art gradient-boosted decision trees are proposed to use for this task and they have been compared with well-known machine learning methods as random forest and multilayer perceptron. It was shown that all machine learning methods provided desirable accuracy which is higher than 95% for solving this problem and proposed gradient-boosted decision trees outperforms random forest and neural network approach in this case in terms of both overall accuracy and f1-score.