Online Recruitment Fraud (ORF) Detection Using Deep Learning Approaches

Abstract

Online Recruitment Fraud (ORF) has emerged as a significant cybersecurity threat, targeting job seekers by imitating legitimate hiring processes to extract sensitive information or financial gain. With the growing reliance on digital recruitment platforms, the detection of fraudulent job postings has become increasingly critical. This paper proposes a deep learning-based approach to identify and mitigate ORF by analyzing linguistic, behavioral, and contextual patterns within job advertisements. Leveraging advanced models such as Bidirectional Long Short-Term Memory (Bi-LSTM), Convolutional Neural Networks (CNN), and Transformer-based architectures, the system effectively distinguishes between genuine and deceptive postings. The dataset comprises real-world job listings annotated for fraud, enabling supervised learning and high-performance evaluation. Experimental results demonstrate that deep learning models significantly outperform traditional machine learning classifiers in accuracy, precision, and recall, achieving over 96% detection accuracy. The proposed system offers a scalable and automated solution to combat ORF, enhancing trust and safety in the online job marketplace.