Персона: Максутов, Артем Артурович
Загружается...
Email Address
Birth Date
Научные группы
Организационные подразделения
Организационная единица
Институт интеллектуальных кибернетических систем
Цель ИИКС и стратегия развития - это подготовка кадров, способных противостоять современным угрозам и вызовам, обладающих знаниями и компетенциями в области кибернетики, информационной и финансовой безопасности для решения задач разработки базового программного обеспечения, повышения защищенности критически важных информационных систем и противодействия отмыванию денег, полученных преступным путем, и финансированию терроризма.
Статус
Фамилия
Максутов
Имя
Артем Артурович
Имя
10 results
Результаты поиска
Теперь показываю 1 - 10 из 10
- ПубликацияТолько метаданныеMethods of Deepfake Detection Based on Machine Learning(2020) Maksutov, A. A.; Morozov, V. O.; Lavrenov, A. A.; Smirnov, A. S.; Максутов, Артем Артурович© 2020 IEEE.Nowadays, people faced an emerging problem of AI-synthesized face swapping videos, widely known as the DeepFakes. This kind of videos can be created to cause threats to privacy, fraudulence and so on. Sometimes good quality DeepFake videos recognition could be hard to distinguish with people eyes. That's why researchers need to develop algorithms to detect them. In this work, we present overview of indicators that can tell us about the fact that face swapping algorithms were used on photos. Main purpose of this paper is to find algorithm or technology that can decide whether photo was changed with DeepFake technology or not with good accuracy.
- ПубликацияТолько метаданныеApplication for Three-Dimensional Graph Data Visualization in VR(2020) Maksutov, A. A.; Zagoskin, I. O.; Uvarov, M. P.; Akhmadov, A. Z.; Максутов, Артем Артурович; Уваров, Максим Павлович© 2020 IEEE.Data visualization is the best way to display information in easy-to-understand visual forms, such as line charts, graphs, pie charts, etc. Data Visualization has emerged in the pre-computer era, but many automated data visualization tools are now available. Now it's easier to use this way of displaying information, because all the work with data visualization in the form of graphics has been transferred to computing systems. The main purpose of data visualization is to present data in such a way that it is easy to understand what is presented and draw conclusions. To do this, the data is converted into visual information, because people are the easiest to perceive and process visual information (and well-designed visualizations use it [1] ).
- ПубликацияТолько метаданныеKnowledge Base Collecting Using Natural Language Processing Algorithms(2020) Maksutov, A. A.; Zamyatovskiy, V. I.; Vyunnikov, V. N.; Kutuzov, A. V.; Максутов, Артем Артурович© 2020 IEEE.Natural language processing (NLP) is one of the most complicated and fast developing area in Computer Science. There are solutions in this area for special cases, but developing one general solution is impossible due to variety of grammatical, syntactic and semantic forms in different languages. The NLP algorithms and methods are used in speech recognition, text analyzing and understanding, speech generation. This paper is focused on application of NLP approaches to understand quasistructured or unstructured data with subsequent inclusion in a knowledge base. The article covers the usage of a graph database as a knowledge base, that allows to show and visualize relationships between different pieces of text according to specified data patterns.
- ПубликацияТолько метаданныеCritical view at quality evaluation systems of stochastic algorithms for information security(2019) Chugunkov, V. I.; Chuzunkov, I. V.; Dyumin, A. A.; Maksutov, A. A.; Liman, D. A.; Чугунков, Илья Владимирович; Дюмин, Александр Александрович; Максутов, Артем Артурович© 2017 IEEE. This paper is devoted to pseudo-random number (PRN) generator testing. The main evaluation systems of statistical properties of pseudo-random sequences formed by PRN generator are considered in the scope of this work. Weaknesses of such systems and ways of tests bypassing were revealed. The example of improving statistical properties of generator through adding statistical randomizer is given. We also propose approach to increasing efficiency of evaluation systems of statistical security of stochastic algorithms based on the usage of artificial neural networks.
- ПубликацияТолько метаданныеMethods of Detecting and Neutralizing Potential DHCP Rogue Servers(2021) Makarova, M. S.; Maksutov, A. A.; Максутов, Артем Артурович© 2021 IEEE.In the continuously evolving environment, computer security has become a convenient challenge because of the rapid rise and expansion of the Internet. One of the most significant challenges to networks is attacks on network resources caused by inadequate network security. DHCP is defenseless to a number of attacks, such as DHCP rogue server attacks. This work is focused on developing a method of detecting these attacks and granting active host protection on GNU/Linux operating systems. Unauthorized DHCP servers can be easily arranged and compete with the legitimate server on the local network that can be the result of distributing incorrect IP addresses, malicious DNS server addresses, invalid routing information to unsuspecting clients, intercepting and eavesdropping on communications, and so on. The goal is to prevent the situations described above by recognizing untrusted DHCP servers and providing active host protection on the local network.
- ПубликацияТолько метаданныеThe Transformer Neural Network Architecture for Part-of-Speech Tagging(2021) Maksutov, A. A.; Zamyatovskiy, V. I.; Morozov, V. O.; Dmitriev, S. O.; Максутов, Артем Артурович; Дмитриев, Святослав Олегович© 2021 IEEE.Part-of-speech tagging (POS tagging) is one of the most important tasks in natural language processing. This process implies determining part of speech and assigning an appropriate tag for each word in given sentence. The resulting tag sequence can be used as is and as a part of more complicated tasks, such as dependency and constituency parsing. This task belongs to sequence-to-sequence tasks and multilayer bidirectional LSTM networks are commonly used for POS tagging. Such networks are rather slow in terms of training and processing large amounts of information due to sequential computation of each timestamp from the input sequence. This paper is focused on developing an accurate model for POS tagging that uses the original Transformer neural network architecture.
- ПубликацияТолько метаданныеDatabase Storage Format for High Performance Analytics of Immutable Data(2021) Rovnyagin, M. M.; Dmitriev, S. O.; Hrapov, A. S.; Maksutov, A. A.; Turovskiy, I. A.; Ровнягин, Михаил Михайлович; Дмитриев, Святослав Олегович; Храпов, Александр Сергеевич; Максутов, Артем Артурович© 2021 IEEE.Most of modern database management systems offer a set of data manipulation operations, which strictly limits the available methods of data storage optimization. This article describes a database storage format that provides a low latency access to stored data with highly optimized sequential data extraction process by prohibiting any data modification after initially loading the data. The current study is aimed at developing a database management system that is suitable for high performance analytics of immutable data and performs better than database management systems with wider applicability. This paper includes developed data storage formats, data load and extraction algorithms and performance measurements.
- ПубликацияТолько метаданныеDevelopment of mesh networks based on the 802.11 family of standards(2019) Maksutov, A. A.; Kondrashkin, K. V.; Durachenko, S. V.; Matveeva, D. V.; Максутов, Артем Артурович© 2019 IEEE A broad range of different proprietary protocols for Internet of Things (IoT) makes it complex to design and orchestrate big systems, which could contain devices based on different protocols. In this article a way to apply mesh topology to the widespread 802.11 b/g/n standards is shown.
- ПубликацияТолько метаданныеReal-time simulation of the GLONASS system signals using SDR(2019) Maksutov, A. A.; Valter, D. A.; Borisenko, G. V.; Ovchinnikov, K. A.; Максутов, Артем Артурович© 2019 IEEE Global navigation satellite systems are being used in numerous of different applications including, self-driving cars and drones. So providing security of this systems is a very important problem. This paper is devoted to do real-time simulation of the GLONASS system signals in order to deceive the satellite signal receiving module. The purpose of this work is to create research tools and increase the level of satellite navigation systems security.
- ПубликацияТолько метаданныеDetection of blockchain transactions used in blockchain mixer of coin join type(2019) Maksutov, A. A.; Alexeev, M. S.; Fedorova, N. O.; Andreev, D. A.; Максутов, Артем Артурович© 2019 IEEE This paper is devoted to both the detection of transactions that can participate in money laundering schemes and the possibility of modification of payment systems based on blockchain technology in the interests of AML/CFT. In the process of work, the research of transaction anonymization method with the use of a decentralized approach based on Coin Join transactions is performed. Also, methods of tracking such transactions, the possibility of their deanonymization and the ability to determine the relationships between users and their transactions are examined. The results show that tracking Coin Join transactions is a feasible task that allows to determine the fact of user participation in the creation of a transaction, which gives additional advantages in the process of detecting transactions involved in money laundering schemes.