scholarly journals Toward to Information Security of AI-Enhanced Weapons

2021 ◽  
pp. 5-11
Author(s):  
Vadim Gribunin ◽  
◽  
Sergey Kondakov ◽  
Keyword(s):  
Machine Learning ◽  
Information Security ◽  
System Analysis ◽  
Learning Technologies ◽  
Point Of View ◽  
Learning Systems ◽  
Security Assessment ◽  
Military Equipment ◽  
The Us ◽  
Article Analysis

Purpose of the article: Analysis of intellectualized weapons using machine learning from the point of view of information security. Development of proposals for the deployment of work in the field of information security in similar products. Research method: System analysis of machine learning systems as objects of protection. Determination on the basis of the analysis of rational priority directions for improving these systems in terms of ensuring information security. Obtained result: New threats to information security arising from the use of weapons and military equipment with elements of artificial intelligence are presented. Machine learning systems are considered by the authors as an object of protection, which made it possible to determine the protected assets of such systems, their vulnerabilities, threats and possible attacks on them. The article analyzes the measures to neutralize the identified threats based on the taxonomy proposed by the US National Institute of Standards and Technology. The insufficiency of the existing regulatory methodological framework in the field of information protection to ensure the security of machine learning systems has been determined. An approach is proposed that should be used in the development and security assessment of systems using machine learning. Proposals for the deployment of work in the field of ensuring the security of intelligent weapons using machine learning technologies are presented.

scholarly journals Analysis of Security of Machine Learning and a proposition of assessment pattern to deal with adversarial attacks

2021 ◽  
Vol 229 ◽  
pp. 01004
Author(s):  
Asmaa Ftaimi ◽  
Tomader Mazri
Keyword(s):  
Machine Learning ◽  
Comparative Study ◽  
Learning Algorithms ◽  
Learning Technologies ◽  
Security Assessment ◽  
Learning Models ◽  
Secure Learning ◽  
Machine Learning Models

Today, Machine Learning is being rolled out in a variety of areas. It is a promising field that can offer several assets and can revolutionize several aspects of technology. Nevertheless, despite the advantages of machine learning technologies, learning algorithms can be exploited by attackers to carry out illicit activities. Therefore, the field of security of machine learning is deriving attention in these times so as to meet this challenge and develop secure learning models. In this paper, we overview a taxonomy that will help us understand and analyze the security of machine learning models. In the next sections, we conduct a comparative study of most widespread adversarial attacks then, we analyze common methods that were advanced to protect systems built on Machine learning models from adversaries. Finally, we discuss a proposition of a pattern designed to ensure a security assessment of machine learning models.

scholarly journals INFORMATION SECURITY ASSESSMENT BASED ON MACHINE LEARNING TECHNOLOGY-FUZZY-GRA-AHP

2019 ◽  
Vol 7 (6) ◽  
pp. 230-240
Author(s):  
Mei-Er Zhuang ◽  
Wen-Tsao Pan
Keyword(s):  
Machine Learning ◽  
Information Security ◽  
Assessment Model ◽  
Security Level ◽  
Learning Technology ◽  
Security Assessment ◽  
Security Risks ◽  
Gray Relation Analysis ◽  
Fuzzy Gra ◽  
Fuzzy Computing

With the advent of the information age, information security has become an urgent problem to be solved. Various application and platforms have not only brought convenience to people, but also brought hidden dangers - information security risks. This paper uses some of the machine learning technology - fuzzy computing and gray relation analysis (GRA), to analyze data of the three major video platforms of China, and takes the information security level as a new criterion to conduct the evaluation of their performance. An assessment model is constructed based on machine learning technology, namely the combination of fuzzy computing and GRA and analytic hierarchy process (AHP). Conclusions can be drawn as follows. First, consumers’ perception of video platform information security level is constantly being strengthened. Second, information security risks are affecting consumers' choice decisions about video platforms, and the weights will continue to increase. Third, video platforms are paying more attention to information security construction.

Cyber Gremlin: social networking, machine learning and the global war on Al-Qaida-and IS-inspired terrorism

2019 ◽  
Vol 27 (3) ◽  
pp. 238-265
Author(s):  
Jamil Ammar
Keyword(s):  
Machine Learning ◽  
Social Networking ◽  
Learning Technologies ◽  
Learning Systems ◽  
Cross Border ◽  
Law And Policy ◽  
Practical Reality ◽  
Global War ◽  
Automated Decision Making

Abstract Among our mundane and technical concepts, machine learning is currently one of the most important and widely used, but least understood. To date, legal scholars have conducted comparatively little work on its cognate concepts. This article critically examines the use of machine learning technologies to suppress or block access to al-Qaida and IS-inspired propaganda. It will: (i) demonstrate that, insofar as law and policy dictate that machine learning systems comply with desired constitutional norms, automated-decision making systems are not as effective as critics would like; (ii) emphasize that, under the current envisaged ‘proactive’ role of networking sites, equating radical and extreme ideas and ideology with ‘violence’ is a practical reality; and (iii) outline a workable strategy for cross-border legal and technical counterterrorism that satisfies the requirements for algorithmic fairness.

A Bayesian Assessment Method of Network Risk

2014 ◽  
Vol 513-517 ◽  
pp. 1684-1687
Author(s):  
Ji Wen Huang ◽  
Zhi Long Deng
Keyword(s):  
Information Security ◽  
Bayesian Network ◽  
Network Inference ◽  
System Analysis ◽  
Expert Knowledge ◽  
Evaluation Process ◽  
Assessment Method ◽  
Security Assessment ◽  
Security Risk ◽  
Information Security Risk

Based on system analysis of information security risk factors and evaluation process, aiming at the uncertainty information is difficult to quantify the evaluation process, Bayesian network inference algorithm, and combined with the inference rules of conditional probability matrix is given by expert knowledge of Bayesian network, the evaluation model of information security risk. Finally an instance of the risk assessment approach on the model is analyzed which demonstrates the rationality and feasibility of this method. So it provides a new method for information security assessment.

scholarly journals ORGANIZATION OF PROTECTION OF KNOWLEDGE CONTROL RESULTS IN DISTANCE LEARNING SYSTEMS

2020 ◽  
Vol 2 (10) ◽  
pp. 144-157
Author(s):  
Oleh Harasymchuk ◽  
Ivan Opirskyy ◽  
Yaroslav Sovyn ◽  
Ivan Tyshyk ◽  
Yevhenij Shtefaniuk
Keyword(s):  
Distance Learning ◽  
Information Security ◽  
User Authentication ◽  
Point Of View ◽  
Learning Systems ◽  
Learning System ◽  
Third Party ◽  
Modern World ◽  
Authorized User ◽  
Functional Components

This paper is devoted to the consideration of information security problems in distance learning systems (DLS), which are becoming widespread in the modern world of educational services, as one of the most effective and promising training systems. The basic information about DLS that exist in the Ukrainian and foreign educational markets is given. The general principle of application of such training, the main functional components and objects of interaction within the framework of DLS are considered. The basic problems of information protection in modern distance learning systems and threats from the point of view of information security for such systems are analyzed in detail, the main goals that an attacker may pursue while carrying out attacks on DLS and vulnerabilities due to which he carries out these attacks are listed. Threats and destabilizing effects of accidental nature are also mentioned. The most common DLS's are compared according to such key parameters as threats of corrupt registration and authentication, threats of reliability of knowledge control results and threats of malicious software implementation. The main focus is on the approaches to the protection of DLS from threats of user substitution (both during the authorization and for an authorized user), threats of the usage of software bots and scripts (by applying the method of protection against the use of scripts based on hidden elements and the method of protection based on behavioral analysis), and also threats to the usage of lectures, electronic reference books and other third-party teaching materials. The mechanism of protection against threats to the reliability of knowledge control results is proposed, which describes actions of the DLS user and the server at the following stages: registration, login, user in the process of filling in the questionnaire, user completed the questionnaire, user starts the test / task and completed testing. This algorithm can be used in any distance learning system to protect from threats to the authenticity of knowledge, and its novelty consists in the usage of methods of user authentication and limiting the functionality available to those users.

scholarly journals Features of Licensing the Activities of Enterprises and Organizations in the Interests of the Ministries of Defense of the Russian Federation

2021 ◽  
pp. 63-74
Author(s):  
Andrey Ivanov ◽  
◽  
Ivan Sprogis ◽  
Igor Shahalov ◽  
◽  
...  
Keyword(s):  
Information Security ◽  
Software Development ◽  
Russian Federation ◽  
System Analysis ◽  
Military Equipment ◽  
Industrial Enterprises ◽  
Development Processes ◽  
The Russian Federation ◽  
Software And Hardware ◽  
Special Examination

The purpose of the article: the best of the existing procedure for assessing the conformity of organizations, industrial enterprises and institutions - developers of software and hardware complexes used in weapons and military equipment. Research methods: system analysis, development of methods. Result: draft methods for checking the archive during special examinations of enterprises and organizations - applicants for a license of the Ministry of Defense of Russia for activities to create information security tools and verify the compliance of software development processes with the requirements of GOST R 56939-2016 during a special examination of licensees of the Ministry of Defense of Russia in the field of creating information security tools have been developed.

scholarly journals Machine Learning Technologies for Sustainability in Smart Cities in the Post-COVID Era

2020 ◽  
Vol 12 (22) ◽  
pp. 9320 ◽  
Author(s):  
Ana De Las Heras ◽  
Amalia Luque-Sendra ◽  
Francisco Zamora-Polo
Keyword(s):  
Machine Learning ◽  
Smart Cities ◽  
Learning Technologies ◽  
Point Of View ◽  
Machine Learning Techniques ◽  
Data Types ◽  
The Sustainable Development ◽  
Learning Techniques ◽  
Exhaustive Study ◽  
Urban Planning And Management

The unprecedented urban growth of recent years requires improved urban planning and management to make urban spaces more inclusive, safe, resilient and sustainable. Additionally, humanity faces the COVID pandemic, which especially complicates the management of Smart Cities. A possible solution to address these two problems (environmental and health) in Smart Cities may be the use of Machine Learning techniques. One of the objectives of our work is to thoroughly analyze the link between the concepts of Smart Cities, Machine Learning techniques and their applicability. In this work, an exhaustive study of the relationship between Smart Cities and the applicability of Machine Learning (ML) techniques is carried out with the aim of optimizing sustainability. For this, the ML models, analyzed from the point of view of the models, techniques and applications, are studied. The areas and dimensions of sustainability addressed are analyzed, and the Sustainable Development Goals (SDGs) are discussed. The main objective is to propose a model (EARLY) that allows us to tackle these problems in the future. An inclusive perspective on applicability, sustainability scopes and dimensions, SDGs, tools, data types and Machine Learning techniques is provided. Finally, a case study applied to an Andalusian city is presented.

RECENT ADVANCES IN MACHINE LEARNING

1992 ◽  
Vol 06 (04) ◽  
pp. 469-511 ◽  
Author(s):  
YVES KODRATOFF
Keyword(s):  
Machine Learning ◽  
Genetic Algorithms ◽  
Point Of View ◽  
Learning Systems ◽  
Learning System ◽  
Reasoning Process ◽  
Body Of Knowledge ◽  
Recent Advances ◽  
Induction Technique ◽  
Flow Of Information

Inference is a very general reasoning process that allows us to draw consequences from some body of knowledge. Machine learning (ML) uses the three kinds of possible inferences, deductive, inductive, and analogical. We describe here different methods, using these inferences, that have been created during the last decade to improve the way machines can learn. We have already presented the most classical approaches in a book (Kodratoff, 1988), and in several review papers (Kodratoff, 1989, 1990a, 1992). These results will be described here very briefly, in order to leave room for newer results. We include also genetic algorithms as an induction technique. We restrict our presentation to the symbolic aspects of connectionism. A learning system can also be viewed as a mechanism skimming interesting knowledge out of the flow of information that runs through it. We present several existing learning systems from this point of view.

scholarly journals USE OF MACHINE LEARNING IN CYBER SECURITY

2021 ◽  
Vol 12 (4) ◽  
pp. 132-142
Author(s):  
Yevhen Ivanichenko ◽  
Mylana Sablina ◽  
Kateryna Kravchuk
Keyword(s):  
Machine Learning ◽  
Information Security ◽  
Cyber Security ◽  
Effective Means ◽  
Learning Technologies ◽  
Cyber Attack ◽  
Security Systems ◽  
Technical Literature ◽  
Artificial Neural ◽  
Self Learning

The urgency of the topic is the integration of machine learning technologies into cybersecurity systems. After getting acquainted with the technical literature, the main technologies of machine learning that are implemented in the organization of cybersecurity were formulated. Acquainted with the main type of artificial neural network used in the prevention and detection of cyber threats and found that the main to consider the general application of machine learning technologies are artificial neural networks based on a multilayer perceptron with inverse error propagation. It is proposed to use indicators of compromise cyberattacks as initial information for automatic machine learning systems. Emphasis is placed on the main types of data that can be used by surveillance subsystems for information security and cybersecurity to perform tasks and prevent, classify and predict cybersecurity events. According to the results of the analysis, the main problem areas for their implementation in information security systems are identified. The problem of using machine learning (ML) in cybersecurity is difficult to solve, because advances in this area open up many opportunities, from which it is difficult to choose effective means of implementation and decision-making. In addition, this technology can also be used by hackers to create a cyber attack. The purpose of the study is to implement machine learning in information security and cybersecurity technology, and to depict a model based on self-learning

Sign in / Sign up

Export Citation Format

Share Document