• International Journal of Computer Science & Network Security
• /
• v.24 no.4
• /
• pp.1-10
• /
• 2024

In the era of big data, the growth of e-commerce transactions brings forth both opportunities and risks, including the threat of data theft and fraud. To address these challenges, an automated real-time fraud detection system leveraging machine learning was developed. Four algorithms (Decision Tree, Naïve Bayes, XGBoost, and Neural Network) underwent comparison using a dataset from a clothing website that encompassed both legitimate and fraudulent transactions. The dataset exhibited an imbalance, with 9.3% representing fraud and 90.07% legitimate transactions. Performance evaluation metrics, including Recall, Precision, F1 Score, and AUC ROC, were employed to assess the effectiveness of each algorithm. XGBoost emerged as the top-performing model, achieving an impressive accuracy score of 95.85%. The proposed system proves to be a robust defense mechanism against fraudulent activities in e-commerce, thereby enhancing security and instilling trust in online transactions.

• International Journal of Computer Science & Network Security
• /
• v.21 no.12spc
• /
• pp.477-482
• /
• 2021

The existing approaches to ensuring the banking security of the state do not take into account the peculiarities of the banking system in the rapid development of the information economy (increasing uncertainty, imbalance and nonlinearity of processes in the banking system under the influence of innovation, institutions, information asymmetry, etc.). A methodological approach to determining the synergetic effect in the implementation of the regulatory influence of the state on the development of innovation processes related to informatization in the banking system, based on the use of differential equations and modelling the sensitivity of innovation processes related to informatization in the banking system, to the regulatory influence of the state to prevent the deployment of risks and threats to economic security of the state in this area has been suggested in the present article.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.2
• /
• pp.747-763
• /
• 2018

Information Technology (IT) plays an increasingly important role for small and medium-sized enterprises. It has become fundamental for these companies to protect information and IT assets in relation to risks and threats that have grown in recent years. This study aims to understand the importance and structure of an information security policy, using a quantitative study that intends to identify the most important and least relevant elements of an information security policy document. The findings of this study reveal that the top three most important elements in the structure of a security policy are the asset management, security risk management and define the scope of the policy. On the other side, the three least relevant elements include the executive summary, contacts and manual inspection. Additionally, the study reveals that the importance given to each element of the security policy is slightly changed according to the sectors of activity. The elements that show the greatest variability are the review process, executive summary and penalties. On the other side, the purpose of the policy and the asset management present a stable importance for all sectors of activity.

• Journal of Information Technology Services
• /
• v.7 no.1
• /
• pp.117-130
• /
• 2008

Multi-attribute risk assessments provide a useful framework for systematic quantitative risk assessment that the security manager can use to prioritize security requirements and threats. In the first step, the security managers identify the four significant outcome attributes(lost revenue, lost productivity, lost customer, and recovery cost). Next. the security manager estimates the frequency and severity(three points estimates for outcome attribute values) for each threat and rank the outcome attributes according to AHP(Analytic Hierarchy Process). Finally, we generate the threat index by using muiti-attribute function and make sensitivity analysis with simulation package(Crystal Ball). In this paper, we show how multi-attribute risk analysis techniques from the field of security risk management can be used by security managers to prioritize their organization's threats and their security requirements, eventually they can derive threat index. This threat index can help security managers to decide whether their security investment is consistent with the expected risks. In addition, sensitivity analysis allows the security manager to explore the estimates to understand how they affect the selection.

• KIPS Transactions on Computer and Communication Systems
• /
• v.3 no.9
• /
• pp.301-310
• /
• 2014

The absence of proactive information security management to ensure availability, accessibility and safety of information can bring serious risks to customers as well as to the organization's performance and competitiveness because improper security management undermines business continuity. This study analyzed the maturity of information security which affects the organizational performance. Through the literature reviews, a research model using the organizational performance as the dependent variable, the risk management process maturity and risk assessment process as independent variables and the information security policy indexes as moderate variables was proposed, and an empirical analysis was made on the basis of survey. The results showed that there was a high causal relationship between information security maturity and organizational performance. However, even if the proportions of information security staff ratio and the information security budget ratio increased, information security maturity did not affect organizational performance. It suggests that information security maturity affects organizational performance, but information security regulations have their limitation as being a catalyst to improve organizational performance.

• International Commerce and Information Review
• /
• v.7 no.3
• /
• pp.135-156
• /
• 2005

The rapidly developed environment by ubiquitous computing make the paradigm from e-trade to u-trade. The purpose of the study is to find out issue and the strategic suggestions that could link together between the e-trade and ubiquitous computing in side of information security. The study include the contents as follows; firstly, the technical explanations under the ubiquitous computing, secondly, e-trade's risks in security technology and lastly, issue and strategic suggestions how link them together in integrated view.

• International Journal of Computer Science & Network Security
• /
• v.22 no.9
• /
• pp.358-368
• /
• 2022

Social media is a window for everyone, individuals, communities, and companies to spread ideas and promote trends and products. With these opportunities, challenges and problems related to security, privacy and rights arose. Also, the data accumulated from social media has become a fertile source for many analytics, inference, and experimentation with new technologies in the field of data science. In this chapter, emphasis will be given to methods of trend analysis, especially ensemble learning methods. Ensemble learning methods embrace the concept of cooperation between different learning methods rather than competition between them. Therefore, in this chapter, we will discuss the most important trends in ensemble learning and their applications in analysing social media data and anticipating the most important future trends.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.10a
• /
• pp.896-899
• /
• 2009

The fear of unauthorized, hidden readouts has dominated the radio frequency identification (RFID) privacy debate. Therefor all published and previous works for privacy mechanisms so far require consumers to actively and explicitly protect read access to their tagged items. This paper introduces the underlying mechanism of our extension to considerations for security and analyzes its tracking resistance and identification performance, and discusses deployment aspects.

• Korea Information Processing Society Review
• /
• v.17 no.2
• /
• pp.18-29
• /
• 2010

In this paper, we surveyed SSO based security management including the knowledge domain of the area of cloud and its relevant components. Cloud computing refers to the delivery of software and other technology services over the Internet by a service provider. SSO refers to the ability to log on to a single security system once, rather than logging on separately to multiple security systems. Existing SSO solutions in cloud computing environment suggest several methods. SSO-based security Issues illustrate these key items in cloud computing environment such as risks and security vulnerabilities of SSO. SSO supports for multiple and different domains in cloud computing environment.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.23 no.6
• /
• pp.1225-1229
• /
• 2013

In this paper, we studied threats and risks that users might enter their passwords without awareness onto phishing and pharming sites, and particularly showed that it was highly likely to leak the secret information of multiple passwords by user experiments. The novel methodology of verifying those threats and risks is the major contribution of this paper. We will extend this work for further verification of our findings.