Pub Date : 2018-12-01DOI: 10.1109/ICONIC.2018.8601203
Skhumbuzo Zwane, Paul Tarwireyi, M. Adigun
Modern tactical wireless network (TWN) communication technologies are not only capable of transmitting voice but also capable of transmitting data. Due to such capabilities, TWN have high security requirements as any security breach can lead to detrimental effects. Hence, securing such an environment is not only a requirement but also a virtual prerequisite to the network centric warfare operational (NCW) theory. One key to securing this environment is to promptly and accurately recognize information warfare attacks directed to the network and respond to them. This is achieved using intrusion detection systems (IDS). However, false detection of nodes in hostile environment remains a major problem that need to be addressed. Recently, machine learning methods and algorithms have shown applicability and are growing research area for cyber security and intrusion detection. Conversely, several decades of research in the field of machine learning have resulted in a multitude of different algorithms for solving a broad range of problems. The question then becomes, which one amongst these machine learning algorithms have the potential to enhance or address IDS issues in TWN. In this paper, seven machine learning classifiers are analyzed; Multi-Layer Perceptron, Bayesian Network, Support Vector Machine (SMO), Adaboost, Random Forest, Bootstrap Aggregation, and Decision Tree (J48). WEKA tool was used to implement and evaluate the classifiers. The results obtained indicate that ensemble-based learning methods outperformed single learning methods when we consider the detection accuracy metrics; AUC, TPR, and FPR. However, ensemble classifiers tend to be slower in in terms of build time and model test time.
{"title":"Performance Analysis of Machine Learning Classifiers for Intrusion Detection","authors":"Skhumbuzo Zwane, Paul Tarwireyi, M. Adigun","doi":"10.1109/ICONIC.2018.8601203","DOIUrl":"https://doi.org/10.1109/ICONIC.2018.8601203","url":null,"abstract":"Modern tactical wireless network (TWN) communication technologies are not only capable of transmitting voice but also capable of transmitting data. Due to such capabilities, TWN have high security requirements as any security breach can lead to detrimental effects. Hence, securing such an environment is not only a requirement but also a virtual prerequisite to the network centric warfare operational (NCW) theory. One key to securing this environment is to promptly and accurately recognize information warfare attacks directed to the network and respond to them. This is achieved using intrusion detection systems (IDS). However, false detection of nodes in hostile environment remains a major problem that need to be addressed. Recently, machine learning methods and algorithms have shown applicability and are growing research area for cyber security and intrusion detection. Conversely, several decades of research in the field of machine learning have resulted in a multitude of different algorithms for solving a broad range of problems. The question then becomes, which one amongst these machine learning algorithms have the potential to enhance or address IDS issues in TWN. In this paper, seven machine learning classifiers are analyzed; Multi-Layer Perceptron, Bayesian Network, Support Vector Machine (SMO), Adaboost, Random Forest, Bootstrap Aggregation, and Decision Tree (J48). WEKA tool was used to implement and evaluate the classifiers. The results obtained indicate that ensemble-based learning methods outperformed single learning methods when we consider the detection accuracy metrics; AUC, TPR, and FPR. However, ensemble classifiers tend to be slower in in terms of build time and model test time.","PeriodicalId":277315,"journal":{"name":"2018 International Conference on Intelligent and Innovative Computing Applications (ICONIC)","volume":"51 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126001809","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}
Pub Date : 2018-12-01DOI: 10.1109/ICONIC.2018.8601226
G. G. K. W. M. S. I. R. Karunarathne, K. Kulawansa, M. Firdhous
Internet of Things has gained the attention of almost everybody due to its capability of monitoring and controlling the environment. IoT helps making decisions supported by real data collected using large number of ordinary day-to-day devices that have been augmented with intelligence through the installation of sensing, processing and communication capabilities. One of the main and important aspects of any IoT device is its communication capability for transferring and sharing data between other devices. IoT devices mainly use wireless communication for communicating with other devices. The industry and the research community have proposed many communication technologies for IoT systems. In this paper, the authors present the results of an in-depth study carried out on the benefits and limitations of these communication technologies.
{"title":"Wireless Communication Technologies in Internet of Things: A Critical Evaluation","authors":"G. G. K. W. M. S. I. R. Karunarathne, K. Kulawansa, M. Firdhous","doi":"10.1109/ICONIC.2018.8601226","DOIUrl":"https://doi.org/10.1109/ICONIC.2018.8601226","url":null,"abstract":"Internet of Things has gained the attention of almost everybody due to its capability of monitoring and controlling the environment. IoT helps making decisions supported by real data collected using large number of ordinary day-to-day devices that have been augmented with intelligence through the installation of sensing, processing and communication capabilities. One of the main and important aspects of any IoT device is its communication capability for transferring and sharing data between other devices. IoT devices mainly use wireless communication for communicating with other devices. The industry and the research community have proposed many communication technologies for IoT systems. In this paper, the authors present the results of an in-depth study carried out on the benefits and limitations of these communication technologies.","PeriodicalId":277315,"journal":{"name":"2018 International Conference on Intelligent and Innovative Computing Applications (ICONIC)","volume":"173 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121613467","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}
Pub Date : 2018-12-01DOI: 10.1109/ICONIC.2018.8601241
M. Nkosi, A. Lysko, S. Dlamini
Networks have become an important feature of our day-to-day to life and therefore, user experience is an imperative goal to be achieved by network operators. Load balancing is a method of improving network performance, availability, minimizing delays and avoiding network congestion. In this paper, we study dynamic load balancing to improve network performance and reduce network response time. The load balancer is applied to OpenFlow SDN network’s data plane with Opendaylight as the controller. The flexibility of the load balancer is tested by using it on two different network topologies. Results show that the load balancer can improve the overall performance of the network and reduce delay. The main contribution of this work is a load balancing mechanism for SDN centralized controller environments which can be employed at any point in time in a network, for example, before network failure or after link failure, to avoid data plane congestion and link overloading.
{"title":"Multi-path Load Balancing for SDN Data Plane","authors":"M. Nkosi, A. Lysko, S. Dlamini","doi":"10.1109/ICONIC.2018.8601241","DOIUrl":"https://doi.org/10.1109/ICONIC.2018.8601241","url":null,"abstract":"Networks have become an important feature of our day-to-day to life and therefore, user experience is an imperative goal to be achieved by network operators. Load balancing is a method of improving network performance, availability, minimizing delays and avoiding network congestion. In this paper, we study dynamic load balancing to improve network performance and reduce network response time. The load balancer is applied to OpenFlow SDN network’s data plane with Opendaylight as the controller. The flexibility of the load balancer is tested by using it on two different network topologies. Results show that the load balancer can improve the overall performance of the network and reduce delay. The main contribution of this work is a load balancing mechanism for SDN centralized controller environments which can be employed at any point in time in a network, for example, before network failure or after link failure, to avoid data plane congestion and link overloading.","PeriodicalId":277315,"journal":{"name":"2018 International Conference on Intelligent and Innovative Computing Applications (ICONIC)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115142367","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}
Pub Date : 2018-12-01DOI: 10.1109/ICONIC.2018.8601262
L. Grobbelaar
A below average throughput of Information Technology students specializing in software development is a challenge that many Universities and Universities of Technology in South Africa face. Contributing factors to this phenomenon are varied at best, but one of the identified factors are that students in this field, especially first year students, find it difficult to conceptualize the associated information and manner of thinking required to become successful in their studies. This is especially true when considering object orientated programming concepts and paradigms that students are required to master as part of their studies. Literary evidence suggests that a high level of working memory, which is associated with abstract thinking ability, is required when learning and applying object orientated programming concepts. The problem becomes more evident and serious if we consider that the Information and Communication Technology sector of a country is largely dependent on the graduating student populous in terms of growing the sector sustainably. A specialized software instrument was developed and tested in an attempt to affect a change in the abstract thinking ability of students from a student sample at a University of Technology. The results of this study focusses on the effect that the instrument realized on the academic performance of first year students related to particularly to object orientated programming and their abstract thinking ability in general as gauged by, amongst other instruments, the General Scholastic Ability Test, or GSAT, rather than focusing on the instrument itself.
{"title":"The Effects of a Software Artefact Designed to Stimulate Abstract Thinking Ability on the Academic Performance in Object Oriented Programming of First Year Information Technology Students","authors":"L. Grobbelaar","doi":"10.1109/ICONIC.2018.8601262","DOIUrl":"https://doi.org/10.1109/ICONIC.2018.8601262","url":null,"abstract":"A below average throughput of Information Technology students specializing in software development is a challenge that many Universities and Universities of Technology in South Africa face. Contributing factors to this phenomenon are varied at best, but one of the identified factors are that students in this field, especially first year students, find it difficult to conceptualize the associated information and manner of thinking required to become successful in their studies. This is especially true when considering object orientated programming concepts and paradigms that students are required to master as part of their studies. Literary evidence suggests that a high level of working memory, which is associated with abstract thinking ability, is required when learning and applying object orientated programming concepts. The problem becomes more evident and serious if we consider that the Information and Communication Technology sector of a country is largely dependent on the graduating student populous in terms of growing the sector sustainably. A specialized software instrument was developed and tested in an attempt to affect a change in the abstract thinking ability of students from a student sample at a University of Technology. The results of this study focusses on the effect that the instrument realized on the academic performance of first year students related to particularly to object orientated programming and their abstract thinking ability in general as gauged by, amongst other instruments, the General Scholastic Ability Test, or GSAT, rather than focusing on the instrument itself.","PeriodicalId":277315,"journal":{"name":"2018 International Conference on Intelligent and Innovative Computing Applications (ICONIC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130434325","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}
Pub Date : 2018-12-01DOI: 10.1109/ICONIC.2018.8601218
Olamide M. Shekoni, Ali N. Hasan, T. Shongwe
Orthogonal frequency division multiplexer (OFDM) is a recent modulation scheme used to transmit signals across power line communication (PLC) channel due to its robustness against some known PLC problems. However, this scheme is greatly affected by the impulsive noise (IN) and often causes corruption with the transmitted bits. Different impulsive noise error correcting methods have been introduced and used to remove impulsive noise in OFDM systems. However, these techniques suffer some limitations and require much signal to noise ratio (SNR) power to operate. In this paper, an approach of designing an effective impulsive-noise error-correcting technique was introduced using three-known artificial neural network techniques (Levenberg-Marquardt, Scaled conjugate gradient, and Bayesian regularization). Findings suggest that both Bayesian regularization and Levenberg-Marquardt ANN techniques can be used to effectively remove the impulsive noise present in an OFDM channel and using the least SNR power.
{"title":"Detecting and Removing the Impulsive Noise in OFDM Channels Using Different ANN Techniques","authors":"Olamide M. Shekoni, Ali N. Hasan, T. Shongwe","doi":"10.1109/ICONIC.2018.8601218","DOIUrl":"https://doi.org/10.1109/ICONIC.2018.8601218","url":null,"abstract":"Orthogonal frequency division multiplexer (OFDM) is a recent modulation scheme used to transmit signals across power line communication (PLC) channel due to its robustness against some known PLC problems. However, this scheme is greatly affected by the impulsive noise (IN) and often causes corruption with the transmitted bits. Different impulsive noise error correcting methods have been introduced and used to remove impulsive noise in OFDM systems. However, these techniques suffer some limitations and require much signal to noise ratio (SNR) power to operate. In this paper, an approach of designing an effective impulsive-noise error-correcting technique was introduced using three-known artificial neural network techniques (Levenberg-Marquardt, Scaled conjugate gradient, and Bayesian regularization). Findings suggest that both Bayesian regularization and Levenberg-Marquardt ANN techniques can be used to effectively remove the impulsive noise present in an OFDM channel and using the least SNR power.","PeriodicalId":277315,"journal":{"name":"2018 International Conference on Intelligent and Innovative Computing Applications (ICONIC)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132373875","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}
Pub Date : 2018-12-01DOI: 10.1109/ICONIC.2018.8601087
S. Mapunya, M. Velempini
The ever-increasing number of wireless network systems brought a problem of spectrum congestion leading to slow data communications. All of the radio spectrums are allocated to different users, services and applications. Hence studies have shown that some of those spectrum bands are underutilized while others are congested. Cognitive radio concept has evolved to solve the problem of spectrum congestion by allowing cognitive users to opportunistically utilize the underutilized spectrum while minimizing interference with other users. Byzantine attack is one of the security issues which threaten the successful deployment of this technology. Byzantine attack is compromised cognitive radios which relay falsified data about the availability of the spectrum to other legitimate cognitive radios in the network leading interference. In this paper we are proposing a security measure to thwart the effect caused by these attacks and compared it to Attack-Proof Cooperative Spectrum Sensing.
{"title":"The Design of Byzantine Attack Mitigation Scheme in Cognitive Radio Ad-hoc Networks","authors":"S. Mapunya, M. Velempini","doi":"10.1109/ICONIC.2018.8601087","DOIUrl":"https://doi.org/10.1109/ICONIC.2018.8601087","url":null,"abstract":"The ever-increasing number of wireless network systems brought a problem of spectrum congestion leading to slow data communications. All of the radio spectrums are allocated to different users, services and applications. Hence studies have shown that some of those spectrum bands are underutilized while others are congested. Cognitive radio concept has evolved to solve the problem of spectrum congestion by allowing cognitive users to opportunistically utilize the underutilized spectrum while minimizing interference with other users. Byzantine attack is one of the security issues which threaten the successful deployment of this technology. Byzantine attack is compromised cognitive radios which relay falsified data about the availability of the spectrum to other legitimate cognitive radios in the network leading interference. In this paper we are proposing a security measure to thwart the effect caused by these attacks and compared it to Attack-Proof Cooperative Spectrum Sensing.","PeriodicalId":277315,"journal":{"name":"2018 International Conference on Intelligent and Innovative Computing Applications (ICONIC)","volume":"125 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132019329","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}
Pub Date : 2018-12-01DOI: 10.1109/ICONIC.2018.8601278
Thabo Mahlangu, Chunling Tu, P. Owolawi
As we see the cyberspace evolve we also see a directly proportional growth of the people using the cyberspace for communication. As a result, the misuse of the cyberspace has given rise to negative issues such as cyberbullying, which is a form of harassing other people using information technology in a deliberate and continual manner. The detection and prevention of cyberbullying becomes critical for safe and health social media platforms. In this paper, a review of the cyberbullying content in Internet, the categories of cyberbullying, data sources containing cyberbullying data for research, and machine learning techniques for cyberbullying detection are overviewed. The main challenges of the cyberbullying detection are demonstrated, including the lack of multimedia content-based detection and availability of public accessible dataset. Suggestions are provided as the conclusion of the overview.
{"title":"A Review of Automated Detection Methods for Cyberbullying","authors":"Thabo Mahlangu, Chunling Tu, P. Owolawi","doi":"10.1109/ICONIC.2018.8601278","DOIUrl":"https://doi.org/10.1109/ICONIC.2018.8601278","url":null,"abstract":"As we see the cyberspace evolve we also see a directly proportional growth of the people using the cyberspace for communication. As a result, the misuse of the cyberspace has given rise to negative issues such as cyberbullying, which is a form of harassing other people using information technology in a deliberate and continual manner. The detection and prevention of cyberbullying becomes critical for safe and health social media platforms. In this paper, a review of the cyberbullying content in Internet, the categories of cyberbullying, data sources containing cyberbullying data for research, and machine learning techniques for cyberbullying detection are overviewed. The main challenges of the cyberbullying detection are demonstrated, including the lack of multimedia content-based detection and availability of public accessible dataset. Suggestions are provided as the conclusion of the overview.","PeriodicalId":277315,"journal":{"name":"2018 International Conference on Intelligent and Innovative Computing Applications (ICONIC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131184427","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}
Pub Date : 2018-12-01DOI: 10.1109/ICONIC.2018.8601274
Kefentse Motshoane, Chunling Tu, P. Owolawi
Prohibition signs are commonly used for safety purposes in order to prevent and protect individuals from dangerous situations. These signs are placed in or around areas whereby they are clearly visible to the public. However, the visually impaired cannot visualize such signs. To help them, this paper proposes a system that combines Convolutional Neural Network (CNN) model and Computer Vision (CV) algorithms to detect and recognize prohibition signs in real scenes. The system uses pre-trained AlexNet model, fine-tuned using Prohibition Signage Boards (PSB) dataset and combined with Maximally Stable Extremal Regions (MSER) and Optical Character Recognition (OCR) techniques for text extraction and classification, to enhance the system performance. The experiments indicate that high recognition accuracies are achieved from a variety of prohibition images and prohibition texts.
{"title":"Prohibition Signage Classification for the Visually Impaired Using AlexNet Transfer Learning Approach","authors":"Kefentse Motshoane, Chunling Tu, P. Owolawi","doi":"10.1109/ICONIC.2018.8601274","DOIUrl":"https://doi.org/10.1109/ICONIC.2018.8601274","url":null,"abstract":"Prohibition signs are commonly used for safety purposes in order to prevent and protect individuals from dangerous situations. These signs are placed in or around areas whereby they are clearly visible to the public. However, the visually impaired cannot visualize such signs. To help them, this paper proposes a system that combines Convolutional Neural Network (CNN) model and Computer Vision (CV) algorithms to detect and recognize prohibition signs in real scenes. The system uses pre-trained AlexNet model, fine-tuned using Prohibition Signage Boards (PSB) dataset and combined with Maximally Stable Extremal Regions (MSER) and Optical Character Recognition (OCR) techniques for text extraction and classification, to enhance the system performance. The experiments indicate that high recognition accuracies are achieved from a variety of prohibition images and prohibition texts.","PeriodicalId":277315,"journal":{"name":"2018 International Conference on Intelligent and Innovative Computing Applications (ICONIC)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129287593","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}
Pub Date : 2018-12-01DOI: 10.1109/ICONIC.2018.8601225
E. Ginters, M. Mezitis, D. Aizstrauta
Humans are an integral part of the nature and to avoid imbalance, the impact of technology on the surrounding environment should be limited. Therefore, green technologies are becoming an important part of economy, politics and science. One of the largest sources of pollution are motorized vehicles, that account for around 14 % of the global greenhouse gas emissions [1]. Use of green transportation within the integrated multimodal transport system is important to minimize carbon emissions [2]. One of these means of transportation is cycling. For cycling to become a fully integrated element within a multimodal transport system and not just a type of tourism, an appropriate infrastructure is necessary – cycling routes, lighting, bike rental, parking, repair services, as well as alignment with other types of transport. Cyclists need route planning tools, information about road surface quality, relief, and usage patterns during different weather conditions and over different days of the week. Infrastructure development projects demand significant financial resources and therefore municipalities need sustainable tools for services design and management. In this article the authors discuss acceptance and sustainability assessment methodology IASAM use to validate the VeloRouter - cycling network designing technology.
{"title":"Sustainability Simulation and Assessment of Bicycle Network Design and Maintenance Environment","authors":"E. Ginters, M. Mezitis, D. Aizstrauta","doi":"10.1109/ICONIC.2018.8601225","DOIUrl":"https://doi.org/10.1109/ICONIC.2018.8601225","url":null,"abstract":"Humans are an integral part of the nature and to avoid imbalance, the impact of technology on the surrounding environment should be limited. Therefore, green technologies are becoming an important part of economy, politics and science. One of the largest sources of pollution are motorized vehicles, that account for around 14 % of the global greenhouse gas emissions [1]. Use of green transportation within the integrated multimodal transport system is important to minimize carbon emissions [2]. One of these means of transportation is cycling. For cycling to become a fully integrated element within a multimodal transport system and not just a type of tourism, an appropriate infrastructure is necessary – cycling routes, lighting, bike rental, parking, repair services, as well as alignment with other types of transport. Cyclists need route planning tools, information about road surface quality, relief, and usage patterns during different weather conditions and over different days of the week. Infrastructure development projects demand significant financial resources and therefore municipalities need sustainable tools for services design and management. In this article the authors discuss acceptance and sustainability assessment methodology IASAM use to validate the VeloRouter - cycling network designing technology.","PeriodicalId":277315,"journal":{"name":"2018 International Conference on Intelligent and Innovative Computing Applications (ICONIC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115127209","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}
Pub Date : 2018-12-01DOI: 10.1109/ICONIC.2018.8601235
R. Trifonov, O. Nakov, V. Mladenov
In the field of Cyber Security there has been a transition from the stage of Cyber Criminality to the stage of Cyber War over the last few years. According to the new challenges, the expert community has two main approaches: to adopt the philosophy and methods of Military Intelligence, and to use Artificial Intelligence methods for counteraction of Cyber Attacks. Тhis paper describes some of the results obtained at Technical University of Sofia in the implementation of project related to the application of intelligent methods for increasing the security in computer networks. The analysis of the feasibility of various Artificial Intelligence methods has shown that a method that is equally effective for all stages of the Cyber Intelligence cannot be identified. While for Tactical Cyber Threats Intelligence has been selected and experimented a Multi-Agent System, the Recurrent Neural Networks are offered for the needs of Operational Cyber Threats Intelligence.
{"title":"Artificial Intelligence in Cyber Threats Intelligence","authors":"R. Trifonov, O. Nakov, V. Mladenov","doi":"10.1109/ICONIC.2018.8601235","DOIUrl":"https://doi.org/10.1109/ICONIC.2018.8601235","url":null,"abstract":"In the field of Cyber Security there has been a transition from the stage of Cyber Criminality to the stage of Cyber War over the last few years. According to the new challenges, the expert community has two main approaches: to adopt the philosophy and methods of Military Intelligence, and to use Artificial Intelligence methods for counteraction of Cyber Attacks. Тhis paper describes some of the results obtained at Technical University of Sofia in the implementation of project related to the application of intelligent methods for increasing the security in computer networks. The analysis of the feasibility of various Artificial Intelligence methods has shown that a method that is equally effective for all stages of the Cyber Intelligence cannot be identified. While for Tactical Cyber Threats Intelligence has been selected and experimented a Multi-Agent System, the Recurrent Neural Networks are offered for the needs of Operational Cyber Threats Intelligence.","PeriodicalId":277315,"journal":{"name":"2018 International Conference on Intelligent and Innovative Computing Applications (ICONIC)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114956286","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：