• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.40 no.10
• /
• pp.1994-2005
• /
• 2015

Voice over IP (VoIP) is a technology for the delivery of voice communications and multimedia sessions over Internet Protocol (IP) networks. Instead of being transmitted over a circuit-switched network, however, the digital information is packetized, and transmission occurs in the form of IP packets over a packet-switched network which consist of several layers of computers. VoIP Service that used the various techniques has many advantages such as a voice Service, multimedia and additional service with cheap cost and so on. But the various frauds arises using VoIP because VoIP has the existing vulnerabilities at the Internet and based on complex technologies, which in turn, involve different components, protocols, and interfaces. According to research results, during in 2012, 46 % of fraud calls being made in VoIP. The revenue loss is considerable by fraud call. Among we will analyze for Toll Bypass Fraud by the SIM Box that occurs mainly on the international call, and propose the measures that can detect. Typically, proposed solutions to detect Toll Bypass fraud used DPI(Deep Packet Inspection) based on a variety of detection methods that using the Signature or statistical information, but Fraudster has used a number of countermeasures to avoid it as well. Particularly a Fraudster used countermeasure that encrypt VoIP Call Setup/Termination of SIP Signal or voice and both. This paper proposes the solution that is identifying equipment of Toll Bypass fraud using those countermeasures. Through feature of Voice traffic analysis, to detect involved equipment, and those behavior analysis to identifying SIM Box or Service Sever of VoIP Service Providers.

• 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.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.5
• /
• pp.545-551
• /
• 2005

The main objective of fraud detection is to minimize costs or losses that are incurred due to fraudulent transactions. Because of the problem's nature such as highly skewed, overlapping class distribution and non-uniform misclassification costs, it is, however, practically difficult to generate a classifier that is near-optimal in terms of classification costs at a desired operating range of rejection rates. This paper defines a performance measure that reflects classifier's costs at a specific operating range and offers a cost-sensitive learning approach that enables us to train classifiers suitable for real-world credit card fraud detection by directly optimizing the performance measure with evolutionary programming. The experimental results demonstrate that the proposed approach provides an effective way of training cost-sensitive classifiers for successful fraud detection, compared to other training methods.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.26 no.6
• /
• pp.1527-1537
• /
• 2016

As increasing of smartphone penetration over the world, various mobile payment services have been emerged and fraud transactions have drastically increased. Although many financial companies have deployed security solutions to detect fraud transactions in on/off-line environment, mobile payment services still lack fraud detection solutions and researches. The mobile payment is mainly comprised of micro-payments and payment environment is different from other payments, so mobile-specialized fraud detection is needed. In this paper, we propose a FDS (Fraud Detection System) based on data mining for mobile payment services. The method of this paper is applied to the real data provided by a PG (Payment Gateway) company in Korea. The proposed FDS consists of two phases; (1) the first phase is focused on classifying transactions at high speed (2) the second is designed to detect abnormal transactions with high accuracy. We could detect 13 transactions per second with 93% accuracy rate.

• ETRI Journal
• /
• v.31 no.1
• /
• pp.92-94
• /
• 2009

We propose a system for mobile-phone fraud detection based on a bidirectional artificial neural network (bi-ANN). The key advantage of such a system is the ability to detect fraud not only by offline processing of call detail records (CDR), but also in real time. The core of the system is a bi-ANN that predicts the behavior of individual mobile-phone users. We determined that the bi-ANN is capable of predicting complex time series (Call_Duration parameter) that are stored in the CDR.

• Asia pacific journal of information systems
• /
• v.28 no.4
• /
• pp.308-319
• /
• 2018

This paper aims at providing valuable insights on Financial Fraud Detection on a mobile money transactional activity. We have predicted and classified the transaction as normal or fraud with a small sample and massive data set using Azure and Spark ML, which are traditional systems and Big Data respectively. Experimenting with sample dataset in Azure, we found that the Decision Forest model is the most accurate to proceed in terms of the recall value. For the massive data set using Spark ML, it is found that the Random Forest classifier algorithm of the classification model proves to be the best algorithm. It is presented that the Spark cluster gets much faster to build and evaluate models as adding more servers to the cluster with the same accuracy, which proves that the large scale data set can be predictable using Big Data platform. Finally, we reached a recall score with 0.73, which implies a satisfying prediction quality in predicting fraudulent transactions.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.12
• /
• pp.3218-3241
• /
• 2023

Financial fraud undermines the sustainable development of financial markets. Financial statements can be regarded as the key source of information to obtain the operating conditions of listed companies. Current research focuses more on mining financial digital data instead of looking into text data. However, text data can reveal emotional information, which is an important basis for detecting financial fraud. The audit opinion of the financial statement is especially the fair opinion of a certified public accountant on the quality of enterprise financial reports. Therefore, this research was carried out by using the data features of 4,153 listed companies' financial annual reports and audits of text opinions in the past six years, and the paper puts forward a financial fraud detection model integrating audit opinions. First, the financial data index database and audit opinion text database were built. Second, digitized audit opinions with deep learning Bert model was employed. Finally, both the extracted audit numerical characteristics and the financial numerical indicators were used as the training data of the LightGBM model. What is worth paying attention to is that the imbalanced distribution of sample labels is also one of the focuses of financial fraud research. To solve this problem, data enhancement and Focal Loss feature learning functions were used in data processing and model training respectively. The experimental results show that compared with the conventional financial fraud detection model, the performance of the proposed model is improved greatly, with Area Under the Curve (AUC) and Accuracy reaching 81.42% and 78.15%, respectively.

• Journal of the Korea Convergence Society
• /
• v.8 no.4
• /
• pp.19-24
• /
• 2017

The growing number of electronic financial transactions (e-banking) has entailed the rapid increase in security threats such as extortion and falsification of financial transaction data. Against such background, rigid security and countermeasures to hedge against such problems have risen as urgent tasks. Thus, this study aims to implement an improved case model by applying the Fraud Detection System (hereinafter, FDS) in a financial corporation 'A' using big data technique (e.g. the function to collect/store various types of typical/atypical financial transaction event data in real time regarding the external intrusion, outflow of internal data, and fraud financial transactions). As a result, There was reduction effect in terms of previous scenario detection target by minimizing false alarm via advanced scenario analysis. And further suggest the future direction of the enhanced FDS.

• International Journal of Computer Science & Network Security
• /
• v.21 no.6
• /
• pp.200-206
• /
• 2021

Fraud in e-commerce transaction increased in the last decade especially with the increasing number of online stores and the lockdown that forced more people to pay for services and groceries online using their credit card. Several machine learning methods were proposed to detect fraudulent transaction. Neural networks showed promising results, but it has some few drawbacks that can be overcome using optimization methods. There are two categories of learning optimization methods, first-order methods which utilizes gradient information to construct the next training iteration whereas, and second-order methods which derivatives use Hessian to calculate the iteration based on the optimization trajectory. There also some training refinements procedures that aims to potentially enhance the original accuracy while possibly reduce the model size. This paper investigate the performance of several NN models in detecting fraud in e-commerce transaction. The backpropagation model which is classified as first learning algorithm achieved the best accuracy 96% among all the models.

• The Journal of Information Systems
• /
• v.18 no.4
• /
• pp.41-57
• /
• 2009

Although financial information is a great influence upon determining of the group which use them, detection of management fraud and earning manipulation is a difficult task using normal audit procedures and corporate credit evaluation processes, due to the shortage of knowledge concerning the characteristics of management fraud, and the limitation of time and cost. These limitations suggest the need of systemic process for !he effective risk of earning manipulation for credit evaluators, external auditors, financial analysts, and regulators. Moot researches on management fraud have examined how various characteristics of the company's management features affect the occurrence of corporate fraud. This study examines financial characteristics of companies engaged in fraudulent financial reporting and suggests a model and system for detecting GAAP violations to improve reliability of accounting information and transparency of their management. Since the detection of management fraud has limited proven theory, this study used the detecting method of outlier(upper, and lower bound) financial ratio, as a real-field application. The strength of outlier detecting method is its use of easiness and understandability. In the suggested model, 14 variables of the 7 useful variable categories among the 76 financial ratio variables are examined through the distribution analysis as possible indicators of fraudulent financial statements accounts. The developed model from these variables show a 80.82% of hit ratio for the holdout sample. This model was developed as a financial outlier detecting system for a financial institution. External auditors, financial analysts, regulators, and other users of financial statements might use this model to pre-screen potential earnings manipulators in the credit evaluation system. Especially, this model will be helpful for the loan evaluators of financial institutes to decide more objective and effective credit ratings and to improve the quality of financial statements.