Research on Modeling of E-banking Fraud Account Identification Based on Federated Learning

Lv, Boliang; Cheng, Peizhe; Zhang, Cheng; Ye, Hong; Meng, Xianzhe; Wang, Xiao

doi:10.1109/dasc-picom-cbdcom-cyberscitech52372.2021.00105

Cited by 7 publications

(5 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each hospital has a subset of all of the patients, and since each patient may have visited multiple hospitals, the patient's features are split between many hospitals. The same situation exists in banking for fraud detection with explainable convex models (Lv et al 2021).…”

Section: Introductionmentioning

confidence: 88%

A Primal-Dual Algorithm for Hybrid Federated Learning

Overman,

Blum,

Klabjan

2024

AAAI

View full text Add to dashboard Cite

Very few methods for hybrid federated learning, where clients only hold subsets of both features and samples, exist. Yet, this scenario is very important in practical settings. We provide a fast, robust algorithm for hybrid federated learning that hinges on Fenchel Duality. We prove the convergence of the algorithm to the same solution as if the model was trained centrally in a variety of practical regimes. Furthermore, we provide experimental results that demonstrate the performance improvements of the algorithm over a commonly used method in federated learning, FedAvg, and an existing hybrid FL algorithm, HyFEM. We also provide privacy considerations and necessary steps to protect client data.

show abstract

Section: Introductionmentioning

confidence: 88%

A Primal-Dual Algorithm for Hybrid Federated Learning

Overman,

Blum,

Klabjan

2024

AAAI

View full text Add to dashboard Cite

show abstract

“…Similarly, [15] suffers from a high complication rate, while [16], [17] and [18] presented a secured system but suffer from resource consumption problems. Moreover, e-banking schemes [19], [20], and [21] lack distributed and decentralized approaches to the security and management of user accounts in electronic banks.…”

Section: Related Research Of E-banking Security and Managementmentioning

confidence: 99%

Transaction Security and Management of Blockchain-Based Smart Contracts in E-Banking-Employing Microsegmentation and Yellow Saddle Goatfish

Al-Zubaidie,

Jebbar

2024

Mesopotamian Journal of CyberSecurity

View full text Add to dashboard Cite

The process security of money transactions is considered an important issue in e-banking. Additionally, it is an enormous problem if never controlled. particular, security should be a combination of fast and sturdy characteristics, which is the subject of previous studies suffered from. Our research attempts to improve the system in which banks deal with the security of financial transactions. This research leverages the idea of microsegmenting the entire system into designated zones to concentrate on security, where each zone has its own rules and limitations. These rules are managed by a smart contract, which decides whether they have been observed to verify the legitimacy of the customer. First, the two-phase commit algorithm (2PC) was used to specify the type of e-banking request. After this, the microsegmentation principle was applied to isolate each type of e-transaction process alone in a separate segment. Then, the yellow saddle goatfish algorithm (YSGA) was used to determine whether the smart contract conditions were optimized. Finally, if the customer is authorized, then the entire transaction process is saved in the blockchain's main ledger and secured by a unique hash. The blockchain application makes our system capable of dealing with large numbers of users in a decentralized manner. In addition, using a hash with each block prevents fraudulent transactions by adversaries. Our system has been examined against several recent well-known assaults/attacks, such as falsification, advanced persistent threat, bribery, spoofing, double spending, chosen text, race, and transaction replay attacks, and has proven to overcome them. In terms of the performance evaluation, we obtained an execution time of approximately 0.0056 nanoseconds, 3.75% complexity, and 1500 KB of memory and disk drive, which is considered low compared to that of state-of-the-art research. Thus, our proposed system is highly acceptable for banking sector applications.

show abstract

“…This is useful in applications such as personalized recommendations, activity recognition, or anomaly detection in smart homes or industrial IoT settings. [48]: Federated learning can enhance privacy in financial services by enabling collaborative model training while keeping sensitive customer data on local servers or devices. Banks or financial institutions can train machine learning models for tasks like fraud detection or credit scoring using locally held customer It is a holistic system that automates selects and uses the most appropriate algorithmic hyperparameters to optimally solve a problem under consideration, approaching it as a model for finding algorithmic solutions where it is solved via mapping between the input and output data.…”

mentioning

confidence: 99%

“…Financial Services [48]: Federated learning can enhance privacy in financial services by enabling collaborative model training while keeping sensitive customer data on local servers or devices. Banks or financial institutions can train machine learning models for tasks like fraud detection or credit scoring using locally held customer data.…”

mentioning

confidence: 99%

“…In this regard, industrial enterprises must thoroughly assess their security policies to ensure that IIoT devices are not vulnerable to threats [68]. Also, providers must understand the significance of adequately configuring the networking device and services and that data privacy entails various processes, such as efficiently removing sensitive information through data segregation [48].…”

mentioning

confidence: 99%

See 1 more Smart Citation

An Overview of Privacy Dimensions on the Industrial Internet of Things (IIoT)

Demertzi

Demertzis

2023

Algorithms

View full text Add to dashboard Cite

The rapid advancements in technology have given rise to groundbreaking solutions and practical applications in the field of the Industrial Internet of Things (IIoT). These advancements have had a profound impact on the structures of numerous industrial organizations. The IIoT, a seamless integration of the physical and digital realms with minimal human intervention, has ushered in radical changes in the economy and modern business practices. At the heart of the IIoT lies its ability to gather and analyze vast volumes of data, which is then harnessed by artificial intelligence systems to perform intelligent tasks such as optimizing networked units’ performance, identifying and correcting errors, and implementing proactive maintenance measures. However, implementing IIoT systems is fraught with difficulties, notably in terms of security and privacy. IIoT implementations are susceptible to sophisticated security attacks at various levels of networking and communication architecture. The complex and often heterogeneous nature of these systems makes it difficult to ensure availability, confidentiality, and integrity, raising concerns about mistrust in network operations, privacy breaches, and potential loss of critical, personal, and sensitive information of the network's end-users. To address these issues, this study aims to investigate the privacy requirements of an IIoT ecosystem as outlined by industry standards. It provides a comprehensive overview of the IIoT, its advantages, disadvantages, challenges, and the imperative need for industrial privacy. The research methodology encompasses a thorough literature review to gather existing knowledge and insights on the subject. Additionally, it explores how the IIoT is transforming the manufacturing industry and enhancing industrial processes, incorporating case studies and real-world examples to illustrate its practical applications and impact. Also, the research endeavors to offer actionable recommendations on implementing privacy-enhancing measures and establishing a secure IIoT ecosystem.

show abstract

Research on Modeling of E-banking Fraud Account Identification Based on Federated Learning

Cited by 7 publications

References 10 publications

A Primal-Dual Algorithm for Hybrid Federated Learning

A Primal-Dual Algorithm for Hybrid Federated Learning

Transaction Security and Management of Blockchain-Based Smart Contracts in E-Banking-Employing Microsegmentation and Yellow Saddle Goatfish

An Overview of Privacy Dimensions on the Industrial Internet of Things (IIoT)

Contact Info

Product

Resources

About