How Artificial Intelligence Can Prevent Social Media Fraud: A Multimodal Detection Framework

Author(s)	Amit Jha
Country	United States
Abstract	Social media fraud has emerged as a critical cybersecurity challenge, causing over USD 1.2 billion in reported losses in 2023 alone. Existing rule-based detection methods fail to address the dynamic and multi-modal nature of these scams. Leveraging my professional experience in AI-driven security initiatives, this study proposes a novel multimodal detection framework integrating Natural Language Processing (NLP), Computer Vision (CV), and Graph Neural Networks (GNNs) to identify fraudulent activities across text, image, and relational network dimensions. Experiments conducted on real-world datasets—Twitter Bot Dataset, Deepfake Detection Challenge, and PhishTank—demonstrate an 18% improvement in detection accuracy compared to traditional systems.
Keywords	Social Media Fraud, Artificial Intelligence, Multimodal Detection, Deepfake Detection, Graph Neural Networks, Cybersecurity.
Field	Engineering
Published In	Volume 16, Issue 4, October-December 2025
Published On	2025-10-04
DOI	https://doi.org/10.71097/IJSAT.v16.i4.9553
Short DOI	https://doi.org/hbb8f4

About IJSAT Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us	Message on WhatsApp	+91-9687-182-185	editor@ijsat.org

International Journal on Science and Technology