Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{201594,
        author = {Hemasalini S and S.Akalya Devi},
        title = {AI-Based Fraud Advertisement Detection Using Text, Link, and Image Analysis},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {5293-5297},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=201594},
        abstract = {The rapid growth of the internet and digital communication platforms has significantly increased the use of online advertisements for promoting products, services, job opportunities, and financial offers. While digital advertising has created new opportunities for businesses and organizations, it has also led to a rise in fraudulent advertisements that deceive users through false claims, fake job postings, misleading investment schemes, and counterfeit product promotions. These fraudulent advertisements often appear on websites, social media platforms, and messaging applications, making it difficult for users to distinguish between genuine and fake advertisements. As a result, many users become victims of online scams, leading to financial loss and security risks. Therefore, an effective and automated solution is required to detect and prevent fraudulent advertisements in the digital environment.
This paper proposes an AI-Based Digital Fraud Advertisement Detection System that aims to automatically analyze advertisements and identify whether they are legitimate or potentially fraudulent. The proposed system utilizes Artificial Intelligence (AI) and Natural Language Processing (NLP) techniques to examine the textual content of advertisements and detect suspicious patterns commonly found in fraudulent messages. By analyzing keywords, phrases, and linguistic patterns, the system can identify advertisements that contain misleading or suspicious information.
In addition to text analysis, the system also performs link analysis to verify the credibility of URLs included in advertisements. Fraudulent advertisements often redirect users to malicious or fake websites, and analyzing the structure and authenticity of links helps detect such threats. Furthermore, the system can incorporate image analysis and Optical Character Recognition (OCR) techniques to extract text from advertisement images and analyze it for possible fraud indicators. This approach enables the system to detect misleading content that may be hidden within images rather than plain text.
The proposed system is implemented as a web-based application using HTML, CSS, and JavaScript for the frontend interface and Python for backend processing. Users can submit advertisement text, links, or images through the web interface, and the system analyzes the input using intelligent algorithms. Based on the analysis results, the system classifies the advertisement as either legitimate or potentially fraudulent and provides feedback to the user.
The implementation of this system demonstrates how artificial intelligence can be effectively applied to improve digital security and protect users from online advertisement scams. By automating the process of advertisement verification, the proposed system helps users identify suspicious advertisements quickly, increases awareness about digital fraud, and contributes to creating a safer online environment. The system also provides a scalable solution that can be further enhanced with advanced machine learning models and larger datasets for improved fraud detection accuracy.},
        keywords = {Artificial Intelligence, Fraud Advertisement Detection, Natural Language Processing, Digital Fraud, Link Analysis, Image Analysis, OCR, Web Application.},
        month = {May},
        }