Securing Online Job Platforms: A Distributed Framework for Combating Employment Fraud in the Digital Landscape

Job scams have existed for a while; advancements in technology have made them more accessible and profitable.By creating fake company websites and posting spurious job listings on well-known online job forums, cybercriminals impersonate actual employers and deceptively interview application victims.They then proceed to request personal information or money from their victims.To effectively address this issue, this work proposes an efficient framework that combines distributed processing, big data analytics, and machine learning to detect such attacks and combat emerging cyber threats.The proposed model employs mining rules to identify and prevent cyber threats in real-time, thereby enhancing user safety and fostering trust in online platforms.The proposed model accurately and efficiently detects fraud by leveraging the power of distributed processing and machine learning.The proposed framework, which provides a reliable approach for identifying fraudulent activity in job postings, is a hybrid approach that incorporates two different analyzing methods based on the data volume and dimension.The first method utilizes Conventional Machine Learning (CML) algorithms, while the second leverages Distributed Machine Learning (DML) algorithms on a distributed platform.The decisionmaking process regarding CML or DML ultimately depends on the specific application requirements, including the data characteristics, the need for distributed computing, and the operating environment.While CML models are a suitable choice for small datasets, DML models are beneficial when working with big datasets.For CML algorithms, the results demonstrate the effectiveness of the Random Forest (RF) algorithm in detection tasks.On the other hand, when the DML algorithms are implemented and evaluated to assess their performance, the experiments confirm that the Distributed Random Forest (DRF) algorithm exhibits high performance in this context.This research contributes to ongoing efforts to strengthen cybersecurity measures on digital platforms, thereby creating a safer online environment for both users and organizations.