Online Fraud Research Articles

Towards a thematic dimensional framework of online fraud: An exploration of fraudulent email attack tactics and intentions

Despite anti-phishing filters, social engineering-based cyber-attacks still result in billions of dollars lost annually, significant personal identity theft, loss of corporate secrets, and espionage. We review the phishing literature on psychological attacks and design tactics employed for deception by attackers. The result reveals the need to continuously identify tactics embedded in fraudulent email content to understand why users still fall prey to phishing attacks. Using the literature as a backdrop, we identify and conceptualize a thematic dimensional framework of fraudulent phishing attacks. This study uses benchmark datasets of fraudulent email to empirically validate the proposed dimensional framework. Specifically, a combination of machine learning-based content analysis and topic modeling found a majority of the discovered topics were labeled against the proposed dimensions. Statistical analysis was employed to provide empirical evidence of the thematic dimensions of fraudulent email attacks. This study thus, not only extends the cybersecurity literature by identifying and validating eight dimensions that enrich our understanding of phishing and attack identification but stimulates cumulative research endeavors to develop yet more comprehensive dimensional frameworks of phishing email attacks.

MS_HGNN: a hybrid online fraud detection model to alleviate graph-based data imbalance

Online transaction fraud has become increasingly rampant due to the convenience of mobile payment. Fraud detection is critical to ensure the security of online transactions. With the development of graph neural network, researchers have applied it to the field of fraud detection. The existing fraud detection methods will solve the class imbalance by sampling, but they do not fully consider the various imbalances in the heterogeneous graph, and the data imbalance will directly affect the performance of the model. This work proposes a hybrid graph neural network model for online fraud detection to address this issue. The three types of imbalance in online transactions are feature imbalance, category imbalance, and relation imbalance, and they are all addressed in the proposed model. The entities with the feature most closely related to the fraudsters will be determined for the feature imbalance, and samples will be taken for further identification in the subsequent training phase. The hybrid model then uses under-sampling in combination with the long-distance sampling to find nodes with high similarity of features for the category imbalance. Finally, we propose a reward/punishment mechanism based on reinforcement learning for relation imbalance, which uses the threshold created by training as the sampling weight between relations. This paper conducts experiments on the public datasets Amazon and Yelp. The experimental results show that the model proposed is 5.61% higher than the best model in the comparison model on Amazon dataset, and 1.58% higher on Yelp dataset.

Consumer Fraud against Older Adults in Digital Society: Examining Victimization and Its Impact.

The European population is aging, which means more people aged sixty-five and over are at risk of financial exploitation. However, there is a lack of consensus regarding whether older persons are at greater risk of fraud than younger counterparts due to physical, economic, and social factors or, rather, whether they are slightly protected from fraud in the digital era due to less frequent online activity. Moreover, little is known about the financial, emotional, psychological, and physical impacts of fraud experiences amongst older generations in digital society. We employ multilevel modelling on a sample of EU citizens (n = 26,735) to analyze these issues. The results show that, holding other factors constant, older adults are more likely to suffer fraud in general, but not fraud via online channels. Identity theft in which the offender attempts to trick the victim by impersonating a reputable organization is found to be particularly relevant for citizens aged sixty-five and above. Older persons are less likely to suffer a financial impact but more likely to experience anger, irritation, embarrassment, and negative impacts on their physical health from fraud in general as well as from online fraud. Many organizations aim to help protect older adults from financial crime and its impacts; thus, the results emphasize the need to understand particular fraud categories suffered by older generations and to design support programs that fully take into account the non-financial impacts of this crime.

MONITORING AND REMOVAL OF FAKE PRODUCT REVIEW USING MACHINE LEARNING (ML)

The employment of Natural Language Processing (NLP) as a means for identifying and eliminating counterfeit products from a dataset is a significant endeavor. The current project employs a Machine Learning (ML) Algorithm to discern fraudulent customer reviews within a given dataset. The algorithm leverages predictive modeling techniques to estimate the authenticity of such reviews, and subsequently assess their validity. The prominence of product reviews as a critical determinant of consumer purchasing behavior in the realm of electronic commerce has led to a concerning escalation in the frequency of counterfeit reviews on websites and applications. It is imperative for the prominent Ecommerce firms to confront the issue of counterfeit product reviews, prior to engaging in the procurement of commodities from established entities. The utilization of this particular approach facilitates the rectification process concerning counterfeit product evaluations, thereby eliminating the prevalence of spammers. This proactive measure works to ensure that there is no potential compromise of trust among users of Ecommerce platforms. Through implementation of this initiative, the enterprise's administration can identify spurious evaluations and subsequently implement appropriate measures directed towards their resolution. The present model has been constructed employing the Naïve Bayes Algorithmic approach. By implementing the algorithm, it is possible to discern spam reviews from those that are legitimate, on websites or applications. To tally the individuals who engage in fraudulent online practices, a dataset is necessary. In our study, the "Amazon Academic Dataset" serves as the fitting reference point to prepare the model and can potentially increase the precision and adaptability of the results.

Fraud Detection in Credit Cards System Using ML with AWS Stage Maker

Abstract: Credit card firms must be able to recognize fraudulent credit card transactions so that clients are not charged for products that they did not purchase. Data Science may be used to solve these issues, and coupled with machine learning, it is of utmost relevance. The goal of this project is to demonstrate how to model a data set using machine learning for credit card fraud detection. The Credit Card Fraud Detection Problem entails modelling previous credit card transactions using information from those that were later determined to be fraudulent. While the globe was under lockdown and movement was confined to an absolute emergency- millions were introduced to the world of internet shopping. The simplicity of internet buying helped ecommerce platforms generate unprecedented sales. It is not surprising that during that time, the rate of online financial fraud also skyrocketed. During the COVID-19 pandemic in 2020 compared to 2019, there was a historic increase of 225 percent in online fraud cases involving credit and debit cards.

"Helping People Get Cheated" to "Anti-Fraud Star"

In recent years, there have been frequent cases of telecom network fraud. Because cunning crooks have long extended their claws to the pure campus. "Post-00" college students grow up in the Internet era and like to participate in online activities and online part-time jobs. In order to prevent college students from falling into the crisis of telecommunications network fraud, although colleges and universities have repeatedly reminded them of security education, the effectiveness of education still needs to be improved. Among them, the fake identity fraud encountered by Xiao Chen is a typical high-incidence telecom network fraud case. By analyzing the causes of cases, the case handling process of ideological and political workers is expounded, and the case reflection and enlightenment are summarized, which provides effective reference ideas for the prevention and control of campus online fraud.

Social media and women’s financial empowerment in the digital economy era in Tanzania

For generations, women in Tanzania have been undermined economically despite efforts from the government, educational institutions, and non-governmental organizations. Besides all of them, the growth of digital communication is emerging, inseparable from transforming women’s empowerment economically, politically, and socially. However, how social media has empowered women financially as an aspect of economic empowerment remains understudied in Tanzania. This study assesses the role of social media in the digital economy to realize its contribution to women’s financial empowerment. Specifically, the study assesses the financial activities of women’s support groups through social media, examines how social media offer economic opportunities to women’s support groups and identify the challenges associated with social media women’s support groups. This study is qualitatively designed and employs in-depth interviews with leaders of women’s support groups in the city of Dodoma. The findings highlight the benefits of WhatsApp social media as a platform for digital economic practices, specifically in enhancing the performance of financial activities. The results also revealed a lack of binding principles among women’s support groups, making them fragile and affecting their growth and sustainability. The study recommends establishing government regulations that bind members who decide to help each other through social media sites. This practice ensures the sustainability of women’s financial groups and avoids online fraud thus, promote women’s financial empowerment and participation in the digital economy in Tanzania.

A Novel Machine learning Algorithms used to Detect Credit Card Fraud Transactions

During the Covid-19 pandemic, the world was under lockdown, and everyone was inside their home. There are so many restrictions for going out, so many companies introduced online shopping, and this online shopping helped more people; the e-commerce platform also increased their revenue; at the same time, online fraud has also risen worldwide. Everyone adopted online shopping during the pandemic. In 2019 India's 2019 credit/debit card fraud rate was 365, according to the National Crime Record Bureau. The developed countries are the highest rate of credit card fraud in 2020 compared to India; for that reason, we have to implement mechanisms that can detect credit theft. The machine learning algorithm with the R program will play an essential role in credit card fraud detection. The following machine learning algorithm will have used for credit card fraud, Random Forest, Logistic regression, Decision trees, and Gradient Boosting Classifiers. The European bank dataset used in our research and the dataset size is 284808. Here we used two classes, the first one is called the positive class (fraud transactions), and the second one is the negative class (genuine transactions). The final result will show us the outperforms of our proposed system.

NFA: A neural factorization autoencoder based online telephony fraud detection

The proliferation of internet communication channels has increased telecom fraud, causing billions of euros in losses for customers and the industry each year. Fraudsters constantly find new ways to engage in illegal activity on the network. To reduce these losses, a new fraud detection approach is required. Telecom fraud detection involves identifying a small number of fraudulent calls from a vast amount of call traffic. Developing an effective strategy to combat fraud has become challenging. Although much effort has been made to detect fraud, most existing methods are designed for batch processing, not real-time detection. To solve this problem, we propose an online fraud detection model using a Neural Factorization Autoencoder (NFA), which analyzes customer calling patterns to detect fraudulent calls. The model employs Neural Factorization Machines (NFM) and an Autoencoder (AE) to model calling patterns and a memory module to adapt to changing customer behaviour. We evaluate our approach on a large dataset of real-world call detail records and compare it with several state-of-the-art methods. Our results show that our approach outperforms the baselines, with an AUC of 91.06%, a TPR of 91.89%, an FPR of 14.76%, and an F1-score of 95.45%. These results demonstrate the effectiveness of our approach in detecting fraud in real-time and suggest that it can be a valuable tool for preventing fraud in telecommunications networks.

More than Money: Examining the Potential Exposure of Romance Fraud Victims to Identity Crime

ABSTRACT Romance fraud occurs when an offender uses the guise of a genuine relationship to defraud an individual for financial gain. Known statistics indicate that millions are lost each year to this form of fraud. However, the potential for romance fraud victims to also experience identity crime as a consequence of their interactions and communications with an offender has yet to be explored. This article begins to address this gap by examining the potential exposure for identity crime in the context of romance fraud using reports lodged with Scamwatch, an Australian online fraud reporting portal. The findings demonstrate few behavioural and demographic characteristics associated with the potential exposure of those targeted by romance fraud to identity crime. However, the article provides insights into how this analysis should inform prevention messaging and victim support services for those targeted by romance fraud.

Fuzzy Authentication System for Online Transaction Fraud Detection Using Geo Location

In the current days, there is an extensive use of online transaction of information from one place to another place and daily, it is incrementing as an exponential growth. Simultaneously, online activities are also performed by the hackers and thus incrementing the online fraud. Therefore, the present research work is an attempt to minimize online fraudulent activities especially for the financial sectors by implementing the different authentication and authorization schemes at the different levels. In the present work authentication scheme has been proposed by implementing the secure One Time Password (OTP) transmission and Personal Identification Number (PIN) which are based on Global Positioning System (GPS) where transaction is performed then GPS has collected the location details from where the transaction has performed and the location of phone in which OTP is received. The concept of distance has calculated with the both GPS locations and used as a authentication factor. Client Financial Control Application (CFCA) is also responsible for authentication for the online transaction which ables to allow or deny transaction based on account status and fuzzy rule based expert system is used to authenticate the distance, transaction time and other parameters while transaction is performed. The main objective of this paper is to provide security for online transactions and to keep track for online fraudulent transaction.

To pay or not to pay: An exploratory analysis of sextortion in the context of romance fraud

Romance fraud, where an offender uses the guise of a genuine relationship for monetary gain, affects millions globally. Further to financial losses, evidence suggests victims may also be targeted for sextortion, where the offender either has images or claims to possess indecent images of a person and attempts to extort them for money. Research exploring the association between romance fraud and sextortion is limited, with little known about the characteristics of victims and their potential for financial loss. This article addresses this gap through a quantitative analysis of those who reported romance fraud which included a threat of sextortion. It identifies those who paid in response to the sextortion threat by a variety of situational and demographic variables and locates this group in the broader context of romance fraud. The implications of this study for an understanding of online fraud victimization are explored in detail.

Comparing Data Mining Classification for Online Fraud Victim Profile in Indonesia

Classification is one of the most often employed data mining techniques. It focuses on developing a classification model or function, also known as a classifier, and predicting the class of objects whose class label is unknown. Categorizing applications include pattern recognition, medical diagnosis, identifying weaknesses in organizational systems, and classifying changes in the financial markets. The objectives of this study are to develop a profile of a victim of online fraud and to contrast the approaches frequently used in data mining for classification based on Accuracy, Classification Error, Precision, and Recall. The survey was conducted using Google Forms, which is an online platform. Naive Bayes, Decision Tree, and Random Forest algorithms are popular models for classification in data mining. Based on the sociodemographics of Indonesia's online crime victims, these models are used to classify and predict. The result shows that Naïve Bayes and Decision Tree are slightly superior to the Random Forest Model. Naive Bayes and Decision Tree have an accuracy value of 77.3%, while Random Forest values 76.8%.

MFGAD: Multi-fuzzy granules anomaly detection

Unsupervised anomaly detection is an important research direction in the process of unsupervised knowledge acquisition. It has been successfully applied in many fields, such as online fraud identification, loan approval, and medical diagnosis. Multi-granularity thinking is an effective information fusion method for solving problems in a multi-granular environment, which allows people to understand and analyze problems from multiple perspectives. However, there are few studies on building anomaly detection models using the idea of multi-fuzzy granules. To this end, this paper constructs a multi-fuzzy granules anomaly detection method by using a fuzzy rough computing model. In this method, a hybrid metric is first used to calculate the fuzzy relations. Then, two ranking sequences are constructed based on the significance of attributes. Furthermore, forward and reverse multi-fuzzy granules are constructed to define anomaly scores based on the ranking sequences. Finally, a multi-fuzzy granules-based anomaly detection algorithm is designed to detect anomalies. The experimental results compared with existing algorithms show the effectiveness of the proposed algorithm.

Theoretical basis and occurrence of internet fraud victimisation: Based on two systems in decision-making and reasoning.

The influencing factors of internet fraud, including demographics, psychology, experience and knowledge of susceptibility, have been widely studied. Research on the psychological mechanism of the victimisation process of internet fraud is relatively scarce but suggests a new research perspective. To summarise and unify the research in this field, this study systematically searched and analysed articles on the psychological decision-making mechanism of online fraud victims. We found that (a) previous researchers consistently believed that the heuristic processing mode was correlated with susceptibility to online fraud and that the systematic processing mode was helpful to detect and identify fraud. From the overall review results, we do not reject this conclusion, but the verification and intrinsic explanation of this relationship need to be further strengthened. (b) Under the heuristic-systematic model (HSM), with the exception of the trait of suspicion, there is no consensus on whether psychological factors (e.g., personality) influence the likelihood of online fraud through the mediating effect of the selection of the two systems. Objective knowledge and experience in specific fields have been found to be able to achieve this path. Information on the influential variables of equipment and habits is emerging, but how they affect network victimisation through the heuristic processing system needs to be further clarified. (c) The measurement of variables is conducted through simulation experiments. There may be a gap between the likelihood of internet fraud victimisation in the simulation experiment and in the real world. (d) The defence strategies under the HSM are intentional explorations, such as content-based cue recognition technology and simulated scene training.

Emerging E-Commerce Trends in India: Opportunities and Challenges

E-commerce refers to the buying and selling of services over the internet as well as the data and money transfers required to complete the sales. It is often referred to as online commerce or electronic commerce. India's e-commerce market is growing quickly. E-commerce is unquestionably a business alternative that must be investigated in the future. E-commerce forecasts indicate a substantial increase in the number of businesses in our nation. Indian e-commerce has shown tremendous growth in recent years, supported by a growing internet user base on mobile phone devices. Due to widespread internet use and advanced electronic devices, India's e-commerce sector is expanding at a rapid rate. Since the majority of people are unaware of online fraud and corruption when conducting transactions, darkness rules. This is by far the greatest difficulty that the Indian e-commerce sector is currently facing. Even financial transactions can be completed quickly and effectively with e-commerce from anywhere in the world. Future generations will feel more at ease making purchases exclusively online. The study's goal is to highlight the idea of e-commerce. The secondary data employed in this study's research approach were listed in various online databases of books, academic papers, and related e-commerce articles. The goal of the current study is to describe the current state of e-commerce in India and to look at its prospects and difficulties.

TINDAK PIDANA MENYEBARKAN BERITA BOHONG MERUGIKAN KONSUMEN MELALUI MEDIA SOSIAL INSTAGRAM

Online fraud is when a writer accesses a website using internet services with the intention of fooling one of the people he intends to target. As a result, lawmakers must be more aggressive in punishing those who commit fraud, particularly online fraud, by having a deterrent effect on others who do so. 1) Did the Respondent's activities satisfy the criteria listed in Article 45A Paragraph (1) of the Electronic Transaction Information Law Number 19 of 2016 (Research Decision Number 1085/pid.sus/2020/PN.bdg)? This is the problem formulation for this final work; 2) How do judges penalize those who commit online fraud using the social media platform Instagram (analysis of decision No. 1085/Pid.sus/2020/PN.Bdg). With secondary data and qualitative analysis, this form of study is normative, and inferential reasoning is used to arrive at findings. Conclusion: 1) The respondent's conduct satisfy the conditions outlined in Article 45A (1); 2) based on the judge's sentencing in that case, which was based only on theory, particularly contemporary, which combines all three types of sentencing theories-absolute, relative, and a combination of the two-and must satisfy the following criteria: Deterrence, education, rehabilitation, social control, rehabilitation, restorative justice.

Police Efforts in Revealing Criminal Acts of Online Fraud

Crimes caused by the development and progress of Information Technology and Telecommunications are crimes related to the internet, or in foreign terms it is often called cybercrime. Cybercrime is a crime that takes advantage of technological developments, especially the internet. The internet, which presents cyberspace with its virtual reality, offers various hopes and conveniences, but behind that, problems arise in the form of a crime called cybercrime, both the computer network system itself and the computer itself which is the vehicle for committing crimes. There are a variety of digital scams such as phishing, lottery scams, video scams, identity theft and scareware. This study uses a normative juridical approach. The normative juridical approach is legal research carried out by examining literature or secondary data as the basic material to be examined by conducting a search of regulations and literature related to the problem under study. The efforts of the police in handling fraud cases online are guided by the Criminal Procedure Code (KUHAP) as well as in the Regulation of the Indonesian National Police Number 6 of 2019), namely as "Investigators and Investigators". The step taken by the Police is to trace the accounts used by the perpetrators of crimes, where the last whereabouts or position of the perpetrators of these crimes are.

Analisis Kesadaran Mahasiswa Terhadap Bahaya Cybercrime Di Media Sosial

Students are one of the largest users of technology and the internet in Indonesia. This is due to the need for technology and the internet to support the continuity of lectures. On the other hand, students also have the potential to become victims of cybercrime. This is due to a lack of education about the dangers of crime on the internet. In addition, the level of concern for securing themselves in the internet world is still low. Cybercrimes that are rife in Indonesia include identity theft, online fraud, bullying, and others. Even though many cybercrimes occur, it is not uncommon for many users to publish their identities and the locations they are currently visiting via social media. On the other hand, the internet network is very well documented by students, this makes students often use free wifi which is not safe so it is at risk of cybercrime. Cybercrime will not occur if users have the knowledge, to be vigilant, especially students who should understand more about the negative effects of social media. Thus it is necessary to carry out an analysis related to user awareness on social media. This research was conducted on 100 student respondents from the Institut Sains & Teknologi AKPRIND Yogyakarta to find out how much the level of awareness and vigilance regarding the dangers of cybercrime is based on the categories of social media awareness, awareness of using e-mail and awareness of crime on the internet. This is evidenced by the results of the average level of awareness of IST Akprind students in using social media, which is included in the high category, which is as much as 82%. On the other hand, awareness of using e-mail and internet crimes is included in the sufficient category, namely 57.5% and 61.5% respectively. Therefore, assistance, education, or socialization is needed from the Institutions, Faculties, and study programs for students who do not have good awareness. This is because there are still students who do not have good vigilance when using e-mail and the internet.

How are financial institutions enabling online fraud? A developmental online financial fraud policy review

PurposeThe criminalization of online financial fraud is examined by analyzing the existing literature, policies and state statutes within the context of the cybercrime ecosystem. Therefore, this paper aims to investigate online fraud policies within the USA and the prevalence of such incidents to explore the effectiveness of current fraud policies.Design/methodology/approachThis examination explores policies related to online fraud within the USA by defining online financial fraud incidents within the context of the cybercrime ecosystem and analyzing such incidents with routine activities theory to emphasize the current legislative inadequacies with provisional policy recommendations.FindingsThis research suggests online financial fraud is not unanimously conceptualized among regulating or criminal institutions. Although federal regulators have governed financial institutions, federal institutions have failed to account for the capabilities of computer-mediated and technological device use (12 USC §1829).Research limitations/implicationsThe limited research analyzing the effectiveness of guardianship that prevents or deters internet-mitigated or dependent financial fraud crimes.Practical implicationsPolicy recommendations include but are not limited to mandating federal and privatized financial institutions to disclose all fraudulent activity to all stakeholders (e.g. customers and local and federal criminal justice agencies).Originality/valueThis paper provides an innovative approach using a criminological theory and policy framework to examine the prevalence of online fraud and the regulations enacted to counteract such violations.