Automated Classification of Cybercrime Complaints using Transformer-based Language Models for Hinglish Texts
Nanda Rani, Divyanshu Singh, Bikash Saha, Sandeep Kumar Shukla
TL;DR
This paper tackles automated classification of Hinglish cybercrime complaints by marrying Hinglish-adapted transformer models with Generative AI-based data augmentation and privacy-preserving preprocessing. The approach, validated on real-world I4C data, shows HingRoBERTa achieving 74.41% accuracy and 71.49% F1, and delivers a production-ready Django-based tool suitable for national cybercrime portals. Key contributions include a 25k-augmented, 14-class dataset, a Hinglish-aware modeling pipeline, and a deployment-ready architecture that emphasizes privacy and scalability. The work demonstrates practical impact for rapid, privacy-conscious triage of cybercrime complaints in multilingual, code-mixed settings, while outlining paths for future enhancement with LLMs and retrieval-based methods.
Abstract
The rise in cybercrime and the complexity of multilingual and code-mixed complaints present significant challenges for law enforcement and cybersecurity agencies. These organizations need automated, scalable methods to identify crime types, enabling efficient processing and prioritization of large complaint volumes. Manual triaging is inefficient, and traditional machine learning methods fail to capture the semantic and contextual nuances of textual cybercrime complaints. Moreover, the lack of publicly available datasets and privacy concerns hinder the research to present robust solutions. To address these challenges, we propose a framework for automated cybercrime complaint classification. The framework leverages Hinglish-adapted transformers, such as HingBERT and HingRoBERTa, to handle code-mixed inputs effectively. We employ the real-world dataset provided by Indian Cybercrime Coordination Centre (I4C) during CyberGuard AI Hackathon 2024. We employ GenAI open source model-based data augmentation method to address class imbalance. We also employ privacy-aware preprocessing to ensure compliance with ethical standards while maintaining data integrity. Our solution achieves significant performance improvements, with HingRoBERTa attaining an accuracy of 74.41% and an F1-score of 71.49%. We also develop ready-to-use tool by integrating Django REST backend with a modern frontend. The developed tool is scalable and ready for real-world deployment in platforms like the National Cyber Crime Reporting Portal. This work bridges critical gaps in cybercrime complaint management, offering a scalable, privacy-conscious, and adaptable solution for modern cybersecurity challenges.