• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.8
• /
• pp.4076-4092
• /
• 2019

Nowadays, most users access internet through mobile applications. The common way to authenticate users through websites forms is using passwords; while they are efficient procedures, they are subject to guessed or forgotten and many other problems. Additional multi modal authentication procedures are needed to improve the security. Behavioral authentication is a way to authenticate people based on their typing behavior. It is used as a second factor authentication technique beside the passwords that will strength the authentication effectively. Keystroke dynamic rhythm is one of these behavioral authentication methods. Keystroke dynamics relies on a combination of features that are extracted and processed from typing behavior of users on the touched screen and smart mobile users. This Research presents a novel analysis in the keystroke dynamic authentication field using two features categories: timing and no timing combined features. The proposed model achieved lower error rate of false acceptance rate with 0.1%, false rejection rate with 0.8%, and equal error rate with 0.45%. A comparison in the performance measures is also given for multiple datasets collected in purpose to this research.

• International Journal of Computer Science & Network Security
• /
• v.22 no.5
• /
• pp.73-78
• /
• 2022

The aim of this paper is to investigate the prevalence of Deep Learning in the literature on Fire & Rescue Service. It is found that deep learning techniques are only beginning to benefit the firefighters. The popular areas where deep learning techniques are making an impact are situational awareness, decision making, mental stress, injuries, well-being of the firefighter such as his sudden fall, inability to move and breathlessness, path planning by the firefighters while getting to an fire scene, wayfinding, tracking firefighters, firefighter physical fitness, employment, prediction of firefighter intervention, firefighter operations such as object recognition in smoky areas, firefighter efficacy, smart firefighting using edge computing, firefighting in teams, and firefighter clothing and safety. The techniques that were found applied in firefighting were Deep learning, Traditional K-Means clustering with engineered time and frequency domain features, Convolutional autoencoders, Long Short-Term Memory (LSTM), Deep Neural Networks, Simulation, VR, ANN, Deep Q Learning, Deep learning based on conditional generative adversarial networks, Decision Trees, Kalman Filters, Computational models, Partial Least Squares, Logistic Regression, Random Forest, Edge computing, C5 Decision Tree, Restricted Boltzmann Machine, Reinforcement Learning, and Recurrent LSTM. The literature review is centered on Firefighters/firemen not involved in wildland fires. The focus was also not on the fire itself. It must also be noted that several deep learning techniques such as CNN were mostly used in fire behavior, fire imaging and identification as well. Those papers that deal with fire behavior were also not part of this literature review.

• Steel and Composite Structures
• /
• v.47 no.4
• /
• pp.523-537
• /
• 2023

This paper proposed a new self-centering brace (SCB), which consists of four post-tensioned (PT) high strength steel strands and energy absorbing steel plate (EASP) clusters. First, analytical equations were derived to describe the working principle of the SCB. Then, to investigate the hysteretic performance of the SCB, four full-size specimens were manufactured and subjected to the same cyclic loading protocol. One additional specimen using only EASP clusters was also tested to highlight the contribution of PT strands. The test parameters varied in the testing process included the thickness of the EASP and the number of EASP in each cluster. Testing results shown that the SCB exhibited nearly flag-shape hysteresis up to expectation, including excellent recentering capability and satisfactory energy dissipating capacity. For all the specimens, the ratio of the recovered deformation is in the range of 89.6% to 92.1%, and the ratio of the height of the hysteresis loop to the yielding force is in the range of 0.47 to 0.77. Finally, in order to further understand the mechanism of the SCB and provide additional information to the testing results, the high-fidelity finite element (FE) models were established and the numerical results were compared against the experimental data. Good agreement between the experimental, numerical, and analytical results was observed, and the maximum difference is less than 12%. Parametric analysis was also carried out based on the validated FE model to evaluate the effect of some key parameters on the cyclic behavior of the SCB.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.6
• /
• pp.1657-1673
• /
• 2023

With the advancement of information technology, criminals employ multiple cyberspaces to promote cybercrime. To combat cybercrime and cyber dangers, banks and financial institutions use artificial intelligence (AI). AI technologies assist the banking sector to develop and grow in many ways. Transparency and explanation of AI's ability are required to preserve trust. Deep learning protects client behavior and interest data. Deep learning techniques may anticipate cyber-attack behavior, allowing for secure banking transactions. This proposed approach is based on a user-centric design that safeguards people's private data over banking. Here, initially, the attack data can be generated over banking transactions. Routing is done for the configuration of the nodes. Then, the obtained data can be preprocessed for removing the errors. Followed by hierarchical network feature extraction can be used to identify the abnormal features related to the attack. Finally, the user data can be protected and the malicious attack in the transmission route can be identified by using the Wrapper stepwise ResNet classifier. The proposed work outperforms other techniques in terms of attack detection and accuracy, and the findings are depicted in the graphical format by employing the Python tool.

• International Journal of Computer Science & Network Security
• /
• v.23 no.7
• /
• pp.91-100
• /
• 2023

Pervasive computing is characterized by a key characteristic that affects the operating environment of services and users. It places more emphasis on dynamic environments where available resources continuously vary without prior knowledge of their availability, while in static environments the services provided to users are determined in advance. At the same time, Cloud computing paradigm introduced flexibility of use according to the user's profile and needs. In this paper, we aimed to provide Context-Aware Transactional Service applications with solutions so that it can be integrated and invoked like any service in the digital ecosystem. Being able to compose is not enough, each service and application must be able to offer a well-defined behavior. This behavior must be controlled to meet the dynamicity and adaptability necessary for the new user's requirements. The motivation in this paper is to offer design patterns that will provide a maximum of automatism in order to guarantee short reaction times and minimal human intervention. Our proposal includes a cloud service model by developing a PaaS service that allows CATS adaptation. A new specification for the validation of CATS model has been also introduced using the ACTA formalism.

• International Journal of Computer Science & Network Security
• /
• v.24 no.8
• /
• pp.159-168
• /
• 2024

Social media sites like as twitter, Facebook and flicker widely used by people, not only as a source of distributing information but also as for communication purpose, with the advancement of technology today. Now a day's one of the most frequently used communication methods are social networks. In various research studies, their use in different fields and the effects of social media on student's behaviors, chat sites and blogs caused by Facebook has been analyzed. In order to obtain the basic data, a general scanning model that is public opinion and views of parents and comments that are openly available across social media sites, used to perceive attitude of graduate students, instead of traditional methods like questionnaires and survey's conduction. A dataset of nearly 20000 reviews of parents was collected from different social media networks about their children's, while in another dataset in which 362 graduate school teachers who observe the students to use social media during classes, labs and in campus during free times, their comments about those students were chosen. As per this study, through different positive and negative factors the detailed analysis has been performed to show effect of social media on student's behavior.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.8 no.2
• /
• pp.107-117
• /
• 2013

The main objective of this study lies at examining economic features of IT security investment and comparing alternative mechanisms to achieve optimal provision of IT security resources within a firm. There exists a paucity of economic analysis that provide useful guidelines for making critical decisions regarding the optimal level of provision of IT security and how to share the costs among different users within a firm. As a preliminary study, this study first argues that IT security resources share some unique characteristics of pure public goods, namely nonrivalry of consumption and nonexcludability of benefit. IT security provision problem also suffers from information asymmetry problem with regard to the valuation of an individual user for IT security goods. Then, through an analytical framework, it is shown that the efficient provision condition at the overall firm level is not necessarily satisfied by individual utility maximizing behavior. That is, an individual provision results in a suboptimal solution, especially an underprovision of the IT security good. This problem is mainly due to the nonexcludability property of pure public goods, and is also known as a free-riding problem. The fundamental problem of collective decision-making is to design mechanisms that both induce the revelation of the true information and choose an 'optimal' level of the IT security good within this framework of information asymmetry. This study examines and compares three alternative demand-revealing mechanisms within the IT security resource provision context, namely the Clarke-Groves mechanism, the expected utility maximizing mechanism and the Groves-Ledyard mechanism. The main features of each mechanism are discussed along with its strengths, weaknesses, and different applicability in practice. Finally, the limitations of the study and future research are discussed.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.28 no.3
• /
• pp.625-633
• /
• 2018

Realm is an open source database developed to replace SQLite, which is commonly used in mobile devices. The data stored in the database must be checked during the digital forensic analysis process for mobile devices because it can help to understand the behavior of the user and whether the mobile device is operating or not. In addition, since the user can intentionally use anti-forensic techniques such as deleting data stored in the database, research on how to recover deleted records is needed. In this paper, we propose a method to recover records that have not been overwritten after deletion based on the analysis of the structure and record and deletion process of the Realm database file.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.25 no.5
• /
• pp.1077-1084
• /
• 2015

Security issues such as an illegal acquisition of personal information and identity theft happen due to using game bots in online games. Game bots collect items and money unfairly, so in-game contents are rapidly depleted, and honest users feel deprived. It causes a downturn in the game market. In this paper, we defined the growth types by analyzing the growth processes of users with actual game data. We proposed the framework that classify hard-core users and game bots in the growth patterns. We applied the framework in the actual data. As a result, we classified five growth types and detected game bots from hard-core users with 93% precision. Earlier studies show that hard-core users are also detected as a bot. We clearly separated game bots and hard-core users before full growth.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.28 no.6
• /
• pp.1439-1448
• /
• 2018

Many electronic document files, including Microsoft Office Word (MS Word), have become a major issue in various legal disputes such as privacy, contract forgery, and trade secret leakage. The internal metadata of OOXML (Office Open XML) format, which is used since MS Word 2007, stores the unique Revision Identifier (RSID). The RSID is a distinct value assigned to a corresponding word, sentence, or paragraph that has been created/modified/deleted after a document is saved. Also, document history, such as addition/correction/deletion of contents or the order of creation, can be tracked using the RSID. In this paper, we propose a methodology to investigate discrimination between the original document and copy as well as possible document file leakage by utilizing the changes of the RSID according to the user's behavior.