{"title":"Malware detection using machine learning based on word2vec embeddings of machine code instructions","authors":"I. Popov","doi":"10.1109/SSDSE.2017.8071952","DOIUrl":"https://doi.org/10.1109/SSDSE.2017.8071952","url":null,"abstract":"Applying machine learning for automatic malware detection is a perspective field of scientific research. One of popular methods in static analysis of executable files is observing machine code instructions that they contain. This paper proposes applying word2vec technique for extracting vector embeddings of machine code instructions and evaluates convolutional neural network-based classifier that uses extracted vectors for malware detection.","PeriodicalId":216748,"journal":{"name":"2017 Siberian Symposium on Data Science and Engineering (SSDSE)","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121467711","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Calculation of number of motifs on three nodes using random sampling of frames in networks with directed links","authors":"E. B. Yudin, M. N. Yudina","doi":"10.1109/SSDSE.2017.8071957","DOIUrl":"https://doi.org/10.1109/SSDSE.2017.8071957","url":null,"abstract":"The task of development of efficient algorithms for estimating the frequency of occurrence of non-isomorphic connected subnets (motifs) on a given number of nodes is an important task of network theory. Combinatorial and logical nature of this problem makes the calculation time-consuming and/or causes high consumption of RAM when estimating networks with hundreds of thousands of nodes. In order to solve the problem this paper develops a random sampling of frames method (MSF), based on a statistical approach, and an algorithm to estimate the occurrence of 3-motifs in networks with directed links is proposed. We suggest implementing the algorithm with the help of parallel computing. The results of numerical data experiments are given. When comparing the developed algorithm with other known algorithms its significant advantages in terms of accuracy, speed and consumption of RAM are revealed in some cases.","PeriodicalId":216748,"journal":{"name":"2017 Siberian Symposium on Data Science and Engineering (SSDSE)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128873639","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Synonymy graph connectivity in graph-based word sense induction","authors":"M. Chernoskutov, Dmitry Ustalov","doi":"10.1109/SSDSE.2017.8071955","DOIUrl":"https://doi.org/10.1109/SSDSE.2017.8071955","url":null,"abstract":"In this paper, we present an approach for synonymy graph augmentation. The approach is based on the equivalence property of the synonymy relation and implies the addition of the missing transitive edges between the potential synonyms in the input synonymy graph. We also conduct the preliminary evaluation of this approach on two datasets for the Russian language and show that it does increase the quality of the graph clustering comparing to the non-augmented input graph.","PeriodicalId":216748,"journal":{"name":"2017 Siberian Symposium on Data Science and Engineering (SSDSE)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131409511","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A. A. Maksutov, I. A. Cherepanov, Maksim S. Alekseev
{"title":"Detection and prevention of DNS spoofing attacks","authors":"A. A. Maksutov, I. A. Cherepanov, Maksim S. Alekseev","doi":"10.1109/SSDSE.2017.8071970","DOIUrl":"https://doi.org/10.1109/SSDSE.2017.8071970","url":null,"abstract":"One of the modern MitM-attacks on HTTPS is attacks using SSLstrip and SSLstrip+ utilities, the latter of which uses a DNS-spoofing type attack. Currently, there are several ways to protect against replacing DNS responses, but there is no available and simple tool for detecting a DNS-spoofing attack. The utility designed for this is called DNSwitch and was described in this article.","PeriodicalId":216748,"journal":{"name":"2017 Siberian Symposium on Data Science and Engineering (SSDSE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122592714","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"The Internet of Things cybersecurity examination","authors":"A. O. Prokofiev, Yulia S. Smirnova, D. Silnov","doi":"10.1109/SSDSE.2017.8071962","DOIUrl":"https://doi.org/10.1109/SSDSE.2017.8071962","url":null,"abstract":"This paper is dedicated to the study of the Internet of Things (IoT) as a potential object of cyberattacks. The main problems of cybersecurity, typical for the IoT devices, as well as the purpose of gaining unauthorized access to these devices are described. The experiment included Internet-Wide scanning for the purpose of detecting smart devices. All captured data were analyzed and systematized. The statistics including the list of countries by rate of IoT devices, accessible via the TELNET protocol, as well as the list of detected device types is provided in the article. The estimate of amount of IoT devices that can be compromised due to weak authentication is also presented.","PeriodicalId":216748,"journal":{"name":"2017 Siberian Symposium on Data Science and Engineering (SSDSE)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130220116","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
I. Chugunkov, E. A. Gridneva, P. V. Kuznetsov, Fedor A. Trofimov, Vladimir I. Chugunkov
{"title":"Issues of increasing the efficiency of replacement blocks for cryptoalgorithms round functions","authors":"I. Chugunkov, E. A. Gridneva, P. V. Kuznetsov, Fedor A. Trofimov, Vladimir I. Chugunkov","doi":"10.1109/SSDSE.2017.8071971","DOIUrl":"https://doi.org/10.1109/SSDSE.2017.8071971","url":null,"abstract":"The article is devoted to the questions of increasing the efficiency of one of the main cryptographic primitives of block encryption — 5-block. The variants of constructing the replacement block based on the block of stochastic data transformation are considered, providing, among other things, improving the statistical properties of the transformed sequences. An approach that consists in replacing not a single byte, but a whole state is proposed. The influence of this approach on the scattering and mixing properties of modern multidimensional block cipher architectures is demonstrated. The possibility of using hybrid architectures for constructing replacement blocks is evaluated.","PeriodicalId":216748,"journal":{"name":"2017 Siberian Symposium on Data Science and Engineering (SSDSE)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116991947","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Grigory R. Khazankin, Sergey Komarov, D. Kovalev, A. Barsegyan, Alexander Likhachev
{"title":"System architecture for deep packet inspection in high-speed networks","authors":"Grigory R. Khazankin, Sergey Komarov, D. Kovalev, A. Barsegyan, Alexander Likhachev","doi":"10.1109/SSDSE.2017.8071958","DOIUrl":"https://doi.org/10.1109/SSDSE.2017.8071958","url":null,"abstract":"To solve the problems associated with large data volume real-time processing, heterogeneous systems using various computing devices are increasingly used. The characteristic of solving this class of problems is related to the fact that there are two directions for improving methods of real-time data analysis: the first is the development of algorithms and approaches to analysis, and the second is the development of hardware and software. This article reviews the main approaches to the architecture of a hardware-software solution for traffic capture and deep packet inspection (DPI) in data transmission networks with a bandwidth of 80 Gbit/s and higher. At the moment there are software and hardware tools that allow designing the architecture of capture system and deep packet inspection: • Using only the central processing unit (CPU); • Using only the graphics processing unit (GPU); • Using the central processing unit and graphics processing unit simultaneously (CPU + GPU). In this paper, we consider these key approaches. Also attention is paid to both hardware and software requirements for the architecture of solutions. Pain points and remedies are described.","PeriodicalId":216748,"journal":{"name":"2017 Siberian Symposium on Data Science and Engineering (SSDSE)","volume":"2015 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128110536","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Anna Kozlova, Alexey Svischev, Olga Gureenkova, Tatiana Batura
{"title":"A hybrid approach for anaphora resolution in the Russian language","authors":"Anna Kozlova, Alexey Svischev, Olga Gureenkova, Tatiana Batura","doi":"10.1109/SSDSE.2017.8071960","DOIUrl":"https://doi.org/10.1109/SSDSE.2017.8071960","url":null,"abstract":"The paper is dedicated to applying a hybrid approach based on rules and machine learning for anaphora resolution in the Russian language. The model combines formal rules, the Extra Trees machine learning algorithm and the Balance Cascade algorithm for working with imbalanced learning sets. A number of features were obtained from the rules or were generated from other features; in addition, the syntactic context was taken into account. A neural network algorithm SyntaxNet was used to analyze the syntactic context.","PeriodicalId":216748,"journal":{"name":"2017 Siberian Symposium on Data Science and Engineering (SSDSE)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116649007","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
V. Kublanov, D. R. Yamaliev, A. Dolganov, E. A. Goncharova
{"title":"Classification of the physical training level by heart rate variability and stabilography data","authors":"V. Kublanov, D. R. Yamaliev, A. Dolganov, E. A. Goncharova","doi":"10.1109/SSDSE.2017.8071963","DOIUrl":"https://doi.org/10.1109/SSDSE.2017.8071963","url":null,"abstract":"In the article the results of the physical training level classification for volunteer subjects by signals of heart rate variability and stabilography by means of linear discriminant analysis are described. The study was conducted on two groups of subjects: high-qualifled athletes (22 people), and young people, not involved in sports (25 people). It was shown that the proposed method makes it possible to identify the subjects' belonging to different groups of physical training level with the accuracy of at least 84%, sensitivity −80% and specificity −91%.","PeriodicalId":216748,"journal":{"name":"2017 Siberian Symposium on Data Science and Engineering (SSDSE)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126466893","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"The iterative procedure modeling for the dynamic parameters estimation at the active identification task","authors":"G. Troshina, A. Voevoda","doi":"10.1109/SSDSE.2017.8071969","DOIUrl":"https://doi.org/10.1109/SSDSE.2017.8071969","url":null,"abstract":"The iterative scheme for the dynamic parameters estimation in the conditions of dynamics noises and the measurement noises is offered in this work. It is supposed that there is an opportunity to give the required input signal on an object. In this work the input signal like a meander is used. The dynamic object modeling and recursive least-squares method modeling are executed in the Simulink environment. The dynamic parameters estimation results are given. The offered approach allows to specify object parameters that is actually in engineering practice.","PeriodicalId":216748,"journal":{"name":"2017 Siberian Symposium on Data Science and Engineering (SSDSE)","volume":"172 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117338963","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}