Telecommunications Fraud Research Articles

Federated Learning for Telecom Fraud Detection: A Privacy-Preserving Approach to Overcoming Data Fragmentation and Enhancing Security

Federated Learning for Telecom Fraud Detection: A Privacy-Preserving Approach to Overcoming Data Fragmentation and Enhancing Security

Policy-driven innovations in fraud prevention: Developing an ARFLGB-XGBoost early warning model to mitigate online romance scams in telecommunication networks

To address the escalating online romance scams within telecom fraud, we developed an Adaptive Random Forest Light Gradient Boosting (ARFLGB)-XGBoost early warning system. Our method involves compiling detailed Online Romance Scams (ORS) incident data into a 24-variable dataset, categorized to analyze feature importance with Random Forest and LightGBM models. An innovative adaptive algorithm, the Adaptive Random Forest Light Gradient Boosting, optimizes these features for integration with XGBoost, enhancing early Online romance scams threat detection. Our model showed significant performance improvements over traditional models, with accuracy gains of 3.9%, a 12.5% increase in precision, recall improvement by 5%, an F1 score increase by 5.6%, and a 5.2% increase in Area Under the Curve (AUC). This research highlights the essential role of advanced fraud detection in preserving communication network integrity, contributing to a stable economy and public safety, with implications for policymakers and industry in advancing secure communication infrastructure.

SUBSCRIPTION FRAUD DETECTION USING AUTOENCODER IN CASE OF ETHIOTELECOM

Nowadays, telecom services are becoming an essential communication and business facilitators. However, the development of telecom services motivates fraudsters for illegal use. Hence, telecom fraud becomes a serious challenge in telecommunication sector by losing telecom revenue. It also results in poor quality of services for their customers. Telecom data, SMS and voice call are not free from security issues. Despite SMS, and USSD services becomes good options over installable mobile based or web based applications due to lesser cost and real time support, the methods provide fixed amount requirements which is not dynamic way to address the need of these services subscribers. The other challenge of these services is that; the services are not safe from frauds as such, especially in GSM switches. Subscription fraud is one type of fraud in today’s telecom business which is a common telecom fraud. The need of fraudsters is to make money illegally or getting telecom services with the intention of not to pay for the service they used. The prime objective of this study is to build a predictive model using deep auto-encoder to detect subscription fraud in case of Ethiotelecom. The performance of fraud detection model is 98.95% validation accuracy on ethiotelecom call detail record dataset using deep neural network autoencoder and CNN-LSTM autoencder algorithms at threshold of 0.0103 and 0173 respectively.

Research on the Criminal Law Response to Telecom Fraud in the Digital Society

With the rapid development of the digital society, telecom fraud has increasingly exhibited characteristics of intelligence, cross-border operations, and concealment, posing serious threats to both the economy and individual interests. However, the current criminal law has many deficiencies in addressing such crimes, making it difficult to effectively curb their spread. This paper analyzes the current state and characteristics of telecom fraud and explores the shortcomings of criminal law in responding to these new forms of fraud in the digital society. It proposes measures such as enhancing the adaptability of the law, improving sentencing standards, and strengthening cross-border judicial cooperation. Furthermore, the paper emphasizes the importance of a coordinated response between technological means and the law, recommending the use of big data and artificial intelligence to improve the investigation and prevention of telecom fraud. The study suggests that only through the deep integration of legal frameworks and technology can the increasingly complex issue of telecom fraud in the digital society be effectively addressed.

Advanced ENF Region Classification Using UniTS-SinSpec: A Novel Approach Integrating Sinusoidal Activation Function and Spectral Attention

The electric network frequency (ENF), often referred to as the industrial heartbeat, plays a crucial role in the power system. In recent years, it has found applications in multimedia evidence identification for court proceedings and audio–visual temporal source identification. This paper introduces an ENF region classification model named UniTS-SinSpec within the UniTS framework. The model integrates the sinusoidal activation function and spectral attention mechanism while also redesigning the model framework. Training is conducted using a public dataset on the open science framework (OSF) platform, with final experimental results demonstrating that, after parameter optimization, the UniTS-SinSpec model achieves an average validation accuracy of 97.47%, surpassing current state-of-the-art and baseline models. Accurate classification can significantly aid in ENF temporal source identification. Future research will focus on expanding dataset coverage and diversity to verify the model’s generality and robustness across different regions, time spans, and data sources. Additionally, it aims to explore the extensive application potential of ENF region classification in preventing crimes such as telecommunications fraud, terrorism, and child pornography.

Research on the use of communication big data and AI artificial intelligence technology to construct telecom fraud prevention behavior portrait

A solid foundation for behavior portrait construction in the fight against telecom fraud is the goal of this research. The study explores the integration of communication AI and Big Data technologies, focusing on the perspective of artificial intelligence. By using insights obtained from a telecom fraud detection model that relies on users’ behavior variations expressed through time-varying signatures, the goal of this study is to enhance fraud prevention strategies in the telecom industry. Through the examination of call detail records and customer profile information, the TeleGuard AI Fraud Prevention Framework (TGAI-FPF) aims to recognize suspicious trends and variations that are potentially suggestive of fraudulent actions. The purpose of the model is to generate behavior portraits that are capable of capturing the distinctive aspects of fraudulent conduct in telecom networks. This will be accomplished through the utilization of advanced analytics and machine learning algorithms. The study highlights the significance of leveraging big data analytics and artificial intelligence technologies to efficiently detect and thwart fraudulent activity in the telecom industry. The results of this study should fortify the defenses of telecom networks against growing fraudulent schemes and help in the development of preventative measures to combat fraud. This is the anticipated manner in which the results will add.

Regional Judicial Cooperation in Combating Cross-Border Telecommunication Fraud: Research and Countermeasures

Regional Judicial Cooperation in Combating Cross-Border Telecommunication Fraud: Research and Countermeasures

Do not ignore heterogeneity and heterophily: Multi-network collaborative telecom fraud detection

The development of mobile communication technologies has enriched human interaction and inevitably led to the proliferation of telecom fraud. While recent studies have paid attention to collaborative fraud in telecom networks, they have examined only voice networks and neglected the collaborative fraud phenomenon in Short Message Service (SMS) networks and across voice and SMS networks. To address this issue, we investigated a telecom dataset with 5.01 million call records and 6.84 million SMS records between 6,106 users and 2.02 million recipients over eight months. On the one hand, we find differences in the evolution pattern of SMS behaviour between fraudsters and normal users. On the other hand, we also confirm the existence of intra-network collaborative fraud in voice networks and SMS networks and inter-network collaborative fraud across voice and SMS networks. To this end, we propose a novel telecom fraud detector, MLCG-FD, which models dynamic individual behaviours and multi-network collaborative relationships. First, a multi-network latent collaborative network (LGC) extractor is designed to extract two intra-network LCGs and one inter-network LCG from voice and SMS networks. Then, we design two behavioural encoders to encode individual voice and SMS behaviour patterns. Finally, a network-based hybrid-pass filter aggregates higher-order neighbour features from different networks. Experiments conducted on two real telecom datasets show that MLCG-FD significantly improves over state-of-the-art methods.

The Current Situation and Prevention of AI Telecom Fraud: Starting from Personal Information Protection

AI telecom fraud is an act of using artificial intelligence deep cooperation and analysis technology to create false information to lure and deceive individuals and illegal possession of money. With the rapid development of the Internet and AI, the number of AI telecom fraud cases has exploded, so how to prevent AI telecom fraud has become an important issue in society. AI telecom fraud has led to a series of problems, such as the illegal collection and malicious disclosure of personal information, criminals using AI to analyze personal information for fraud, and the industry does not adequately supervise the collection and use of personal information by companies. This article uses case analysis, normative analysis, and comparative research methods to analyze the above three problems and proposes the solution, including establishing a complete legal regulatory system for personal information protection and the prevention and control of AI telecom fraud, and strengthening industry supervision. It is hoped that by applying the above-mentioned solutions, the protection of personal information and the prevention and control of AI telecom fraud can be strengthened, and the development of AI telecom fraud prevention and control in China can be promoted.

A Pragmatic Study on the Identity Construction of Deceptive Telecom Discourse

Taking identified fraud telephone recordings as the corpus, the study first analyses the lexicon and overall structure of fraud discourse from the perspective of pragmatics and then explores the identities constructed by fraudsters. It found that, in deceptive telecom discourse, address forms and technical terms are used to construct the turn, and the fraud conversation has a relatively complete structure, including a beginning, problem construction, problem solving, and a closing. In addition, the lexical choice and the overall structure of deceptive conversation help to construct the fraudster’s individual identity, interpersonal identity and group identity. Individual identity includes the real identity as a fraudster and the false identity as a help seeker; interpersonal identity involves identity as a relative or superior; and group identity can be divided into institutional identity and professional identity. This study aims to enhance people’s awareness of fraud and assist in identifying the fraudulent identities of scammers, thereby reducing the occurrence of telecom fraud incidents.

On the Exploration and Practice of the Anti-Fraud Work System of College Students under the Perspective of “Three-Fully Education” —— Take Shenzhen Polytechnic University as an Example

In recent years, college students have suffered from frequent Internet fraud incidents. Criminals make use of students’ vanity, petty profit, and simple mentality, taking a variety of fraud means, resulting in some students bearing huge property losses and mental pressure. Telecom fraud has gradually evolved into a serious social problem, and now domestic colleges and universities have become the hardest hit areas of telecom network fraud, and many problems exposed behind it deserve our deep reflection. The paper has analyzed college students’ telecom fraud types and situation, the characteristics of telecom fraud, called on the concept of “three-fully education”, which explores the problem by “fully improving ideological understanding”, “fully accurate classification management,” “fully intensifying governance” to fight fraud work, and improve college students’ telecom fraud awareness and self-protection ability.

Analysis On the Criminal Jurisdiction Path of Foreign-Related Cybercrime from The Perspective of Transnational Telecom Fraud

Analysis On the Criminal Jurisdiction Path of Foreign-Related Cybercrime from The Perspective of Transnational Telecom Fraud

Determination Of the Amount of Cross-Border Telecommunication Fraud Crime in The Era of Big Data

Determination Of the Amount of Cross-Border Telecommunication Fraud Crime in The Era of Big Data

Telecommunication fraud resilient framework for efficient and accurate detection of SMS phishing using artificial intelligence techniques

Telecommunication fraud resilient framework for efficient and accurate detection of SMS phishing using artificial intelligence techniques

Does financial literacy contribute to facilitating residents in safeguarding their rights as financial consumers?A three-stage study based on the perspective of “fraud” phenomenon

Utilizing microdata from six provinces in East China, this study centers on the phenomenon of “fraud," employing a three-stage Probit model with dual sample selectivity to explore the impact of financial knowledge on residents' safeguarding of financial consumer rights and interests. This methodological approach effectively addresses estimation bias arising from concerns related to dual sample selectivity. The process of residents safeguarding their rights and interests when confronted with fraud unfolds in three sequential stages: “pre-fraud prevention, during fraud loss avoidance, and post-fraud rights protection." Key findings indicate that, on the whole, higher levels of financial knowledge foster residents' protection of financial consumer rights and interests. Specifically, heightened financial literacy is associated with an increased likelihood of encountering fraud, a reduced probability of incurring losses post-fraud, and an enhanced propensity for pursuing rights protection thereafter. Moreover, heterogeneity analysis reveals that the impact of financial knowledge is more pronounced among middle-aged and elderly individuals, rural inhabitants, and women. Furthermore, concerning various types of fraud, the amplification effect of financial knowledge is particularly evident in cases of telecom fraud and online fraud, though not in traditional fraud cases. Additionally, moderation effect analysis underscores that, overall, heightened attention to information, improved digital literacy, and increased social interaction can reinforce the positive influence of financial knowledge. This paper provides valuable insights for strengthening the protection of residents' financial rights and ensuring the security of their assets.

Exploring Telecommunication Fraud from A Student's Perspective

With the rapid development of the information society, the structure of crime has undergone significant changes, and traditional crime has continued to decline, in contrast to which the new type of cybercrime represented by telecommunication network fraud has become the current major form of crime. In the public's perception, most of the victims of telecommunication network fraud are elderly people who are not familiar with the network, middle-aged people who are frequently involved in financial investment and the financial market, or young people who have just entered the workplace and are in urgent need of stability. However, students, who seem to have nothing to do with money, are becoming a new target for fraudsters. Part of the reason is because of the students a large number of personal information has been improperly collected, use, another part of the reason is that the students just because there is no source of money, but in the face of temptation has no resistance, especially for the students who have been addicted to online games, excessive consumption, almost unable to resist a variety of deception.

Reinforced Cost-Sensitive Graph Network for Detecting Fraud Leaders in Telecom Fraud

Reinforced Cost-Sensitive Graph Network for Detecting Fraud Leaders in Telecom Fraud

Empirical Research on the High Incidence of Crime of Assisting Information Network Criminal Activities in Telecommunication Fraud Cases Based on 26, 121 Judgment Documents

Empirical Research on the High Incidence of Crime of Assisting Information Network Criminal Activities in Telecommunication Fraud Cases Based on 26, 121 Judgment Documents

Feasibility Study on China-ASEAN Cooperation in the Forewarning Mechanism Against Telecom Fraud

Along with the implementation of the Belt and Road Initiative and the deepening of regional police cooperation, China and ASEAN have jointly reached remarkable achievement on cyberspace security governance, whereas facing numerous new counter-cybercrime challenges at the same time, exemplified by diversified modes and high concealment. Undeniably, China and ASEAN have accumulated abundant experience through formal conferences and informal forums, but the low institutionalization of China-ASEAN cooperation has made it hard to timely and effectively respond to the protean transborder telecom frauds. Forewarning mechanism, as an innovative method to combat telecom fraud, could significantly make up for the deficiency under the current China-ASEAN cooperative system, while enriching the Belt and Road cooperation Initiative, raising the efficiency of controlling cybercrimes, exploiting the advantage of Chinese Internet+ strategy.

Feature difference-aware graph neural network for telecommunication fraud detection

With the continuous escalation of telecommunication fraud modes, telecommunication fraud is becoming more and more concealed and disguised. Existing Graph Neural Networks (GNNs)-based fraud detection methods directly aggregate the neighbor features of target nodes as their own updated features, which preserves the commonality of neighbor features but ignores the differences with target nodes. This makes it difficult to effectively distinguish fraudulent users from normal users. To address this issue, a new model named Feature Difference-aware Graph Neural Network (FDAGNN) is proposed for detecting telecommunication fraud. FDAGNN first calculates the feature differences between target nodes and their neighbors, then adopts GAT method to aggregate these feature differences, and finally uses GRU approach to fuse the original features of target nodes and the aggregated feature differences as the updated features of target nodes. Extensive experiments on two real-world telecom datasets demonstrate that FDAGNN outperforms seven baseline methods in the majority of metrics, with a maximum improvement of about 5%.