AI Based Fake Content Detection System

Abstract

The LASSO: AI?Powered Fake Content Detection System is an intelligent digital application designed to identify and analyze potentially fake, manipulated, or malicious digital content across multiple formats such as text, images, audio, video, and URLs. In today\'s rapidly evolving digital environment, misinformation, deepfakes, phishing links, and AI?generated content have become major threats that can mislead individuals, compromise privacy, and cause financial or social harm. Traditional methods of identifying fake content often rely on manual verification or limited detection tools, which are inefficient and time?consuming. This project aims to address these challenges by developing a centralized and automated platform that uses artificial intelligence to detect suspicious or fake digital content quickly and accurately. The LASSO system provides users with a simple and interactive interface where they can input or upload different types of media for analysis. Users can paste suspicious text messages, upload images, audio files, or videos, and even scan URLs to verify their authenticity. The system processes the input using AI?based detection techniques and returns a result indicating whether the content is genuine, suspicious, or potentially fake, along with a confidence score. The application also maintains a scan history and generates downloadable reports, helping users keep track of previously analyzed content. Technically, the system is developed using the Flutter framework for the frontend, enabling a modern and responsive cross?platform mobile application interface. The backend integrates AI?based detection services and APIs that analyze the uploaded content and return detection results. The system architecture is designed to ensure efficient data processing, user?friendly navigation, and secure handling of uploaded files. Additional modules such as notification alerts, result visualization, and report generation further enhance the functionality of the application. In conclusion, the LASSO Fake Content Detection System provides a powerful solution to combat digital misinformation and fraudulent media by leveraging artificial intelligence and modern mobile technologies. By enabling users to quickly verify the authenticity of digital content, the system improves digital awareness, enhances online security, and contributes to the broader effort of reducing the spread of fake information in the digital world.

Introduction

The rapid growth of internet and social media has led to a surge in misinformation, fake news, phishing links, and deepfake media, making manual verification difficult and unreliable. To address this issue, the LASSO: AI-Powered Fake Content Detection System is proposed as an intelligent, user-friendly platform that analyzes text, images, audio, video, and URLs to detect fake or manipulated content.

The system allows users to upload or input suspicious content and receive instant results with a confidence score. It also includes features like scan history, reports, notifications, and result visualization to enhance usability and tracking.

Unlike existing systems that are fragmented and limited to single content types, LASSO provides a centralized and integrated solution using AI and machine learning techniques. It is built using Flutter for the frontend and FastAPI for the backend, with multiple detection modules and machine learning models handling different media types.

The architecture ensures smooth data flow from user input to analysis and result generation, supported by APIs and database storage. Key modules include user interaction, content analysis, machine learning processing, and API integration.

The system improves efficiency, accessibility, and digital security by automating fake content detection. It helps users make informed decisions, reduces the spread of misinformation, and enhances cybersecurity awareness.

Overall, LASSO is a scalable, secure, and comprehensive solution that simplifies verification of digital content and addresses the limitations of traditional and existing tools.

Conclusion

The LASSO: AI?Powered Fake Content Detection System successfully demonstrates the development and implementation of a modern mobile application designed to detect and analyze fake or manipulated digital content. The system provides a centralized platform where users can verify the authenticity of different types of media including text, images, audio, video, and URLs. By integrating advanced technologies such as Flutter for the mobile interface, FastAPI for backend services, and SQLite for data storage, the application delivers a reliable, efficient, and user?friendly solution for identifying suspicious digital content. The implementation of this system highlights the growing importance of technological solutions in combating digital misinformation and fraudulent online activities. Through a simple and intuitive interface, users can easily submit suspicious content and receive analysis results along with confidence scores. Features such as multiple detection modules, result visualization, and scan history management enhance the usability of the application and allow users to verify information quickly and effectively. The integration of machine learning-based detection methods further strengthens the system’s capability to identify manipulated or misleading digital content. From a technical perspective, the project demonstrates the effective integration of mobile development frameworks, backend APIs, and machine learning processing modules within a unified architecture. The modular design of the system ensures scalability, maintainability, and efficient communication between the frontend and backend components. The use of Flutter ensures a responsive and interactive mobile interface, while FastAPI enables high?performance backend processing and seamless API communication with detection modules. In conclusion, the LASSO Fake Content Detection System successfully achieves its primary objective of providing a smart and efficient platform for detecting fake digital content. The system improves digital awareness, enhances online safety, and helps users make informed decisions when interacting with online information. With its scalable architecture and modular design, the application can be further expanded in the future by integrating more advanced machine learning models, cloud-based processing, and real-time threat detection features. This project represents a significant step toward improving digital content verification and promoting a safer online environment.

References

[1] A. Géron, Hands?On Machine Learning with Scikit?Learn, Keras, and TensorFlow, 2nd Edition, O’Reilly Media, 2019. [2] Ian Goodfellow, Yoshua Bengio, and Aaron Courville, Deep Learning, MIT Press, 2016. [3] Mark Lutz, Learning Python, 5th Edition, O’Reilly Media, 2013. [4] Eric Matthes, Python Crash Course: A Hands?On, Project?Based Introduction to Programming, 2nd Edition, No Starch Press, 2019. [5] Flutter Documentation, Flutter Development Framework, Available at: https://flutter.dev/docs(Accessed: October 2025). [6] FastAPI Official Documentation, FastAPI Framework for Building APIs, Available at: https://fastapi.tiangolo.com/(Accessed: October 2025). [7] SQLite Documentation, SQLite Database Engine, Available at: https://www.sqlite.org/docs.html(Accessed: October 2025). [8] Django Official Documentation, Django Web Framework, Available at: https://docs.djangoproject.com/(Accessed: October 2025). [9] W3Schools, Web Development Tutorials (HTML, CSS, JavaScript), Available at: https://www.w3schools.com/(Accessed: October 2025). [10] GeeksforGeeks, Machine Learning and Web Development Tutorials, Available at: https://www.geeksforgeeks.org/(Accessed: October 2025). [11] TutorialsPoint, Django Framework Tutorial, Available at: https://www.tutorialspoint.com/django/(Accessed: October 2025). [12] Stack Overflow, Programming Solutions and Developer Community, Available at: https://stackoverflow.com/(Accessed: October 2025). [13] Research Paper: S. Agarwal and T. Varshney, “Detection of Fake News Using Machine Learning Techniques,” International Journal of Computer Applications, Vol. 183, No. 15, 2022.

Copyright

Copyright © 2026 Sambathkumar N, Sivaraman M, Thirukumaran R, Mrs. R. Vijayalakshmi. This 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.