Python
Aim:
The aim of this research is to develop ReACT_OCRS, an AI-powered voice-based cybercrime reporting system that enables anonymous and multilingual audio complaint submissions. It seeks to enhance accessibility, accuracy, and security in cybercrime reporting through speech recognition.
Abstract:
Victims and witnesses of cybercrime often hesitate to report incidents due to concerns about privacy, complexity, and fear of retaliation. Traditional reporting mechanisms that rely on manual data entry create accessibility barriers and delay response times. To overcome these challenges, this paper presents ReACT_OCRS, an AI-driven voice-based cybercrime reporting system that enables victims and witnesses to anonymously submit complaints through audio recordings. By leveraging speech recognition transformers, advanced language models, and encryption techniques, the system processes real-time multilingual voice inputs, extracts meaningful information, and classifies reports with high precision using a hybrid voting mechanism. Experimental evaluations conducted on both synthetically generated and human-validated datasets demonstrate the system’s ability to accurately transcribe, classify, and securely process audio complaints while preserving user anonymity. Overall, this work enhances the cybercrime reporting process by making it more accessible, efficient, and secure, thereby encouraging greater participation from victims and witnesses.
Proposed System
The proposed system is a Java Spring Boot–based web application designed to provide a secure, anonymous, and intelligent cybercrime reporting platform. The system operates with two main roles — User and Cyber Officer — ensuring an organized and transparent complaint management process. In this application, a user can register without revealing personal details, maintaining full anonymity. Upon registration, the system automatically generates a unique user ID for each individual. After logging in, the user can submit a complaint using two mechanisms — by uploading an audio file or by recording the audio directly through the application. Once a complaint is submitted, the user can track and view the status of their complaint in real time through the application dashboard. On the cyber officer side, the system provides an interface to view and manage all submitted complaints. Each complaint undergoes an evaluation process where the officer uses AI-based prediction techniques to convert the audio input into text and analyze its content. Based on the prediction results, the officer can classify the complaint as genuine or false, and subsequently accept or reject it for further investigation. To enhance security and data privacy, the system incorporates the concept of federated learning, ensuring that complaint data is processed locally without sharing sensitive user information with external servers. This approach strengthens privacy while allowing the model to continuously learn and improve from distributed data. Overall, the proposed system provides a secure, anonymous, and intelligent platform for cybercrime reporting, offering users a simple and accessible way to file complaints while enabling cyber officers to efficiently evaluate and act on reported incidents.
Advantages of the proposed System:
AI-Driven Analysis:
The system uses AI to convert audio complaints into text and intelligently classify them as genuine or false.
Anonymity and Privacy :
Users can register and submit complaints without revealing personal information, ensuring complete anonymity.
Enhanced Security with Federated Learning:
Complaint data is processed locally, preventing sensitive information from being shared with external servers.
Reviews
There are no reviews yet.