SECURE GRAM: AI-POWERED SECURE MESSAGING PLATFORM FOR REAL TIME DRUG DETECTION AND PREVENTION

Author

Manya B. M., Impana M.P., Laxmi K., Kruthika G.R.

Abstract

 The increasing prevalence of digital messaging platform has made difficult to detect drug-related communications, especially slangs, abbreviations, and coded terms. Secure Gram, an AI-powered secure messaging platform intended to enhance online communication safety by detecting drug-related content in real time. Utilizing Natural Language Processing (NLP), Secure Gram identifies potentially concerning messages and includes features such as message detection, real-time communication, an administrative dashboard for monitoring flagged content, and an AI-driven wellness chatbot that offers supportive guidance to users. The platform aims to raise awareness and facilitate early intervention regarding drug-related issues. The research investigates current detection methods and suggests the integration of machine learning techniques to enhance classification accuracy. Evaluation metrics like precision, recall, F1-score, and interface latency will be employed to determine the feasibility of combining automated message detection with wellness support within the messaging framework.

Keywords

Secure gram, Drug-Related Message Detection, Natural Language processing, Machine learning, AI Wellness Chatbot

Full Text:

Download Paper PDF

References

[1] Ahmad M, Waqas M, Matyrshin I, and Sidorov G. “Leveraging large language” for Multi-Class and Multi-Label Detection of Drug Use and

Overdose Symptoms on Social Media, 2025

[2] Zhang X, “Developing Large language Models to Detect adverse Drug Events in posts on X”, Journal of the American Medical Informatics

Association , 2024

[3] Devlin, J., Chang, M. W., Lee, K., and Toutanova, K., “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding,” Proceedings of NAACL-HLT, , 2019.

[4] Raj S, Tiwari A, “Bert” Based Transformers lead the way in extraction of Health Information from Social Media, 2021

[5] Portelli, B, Passabi of Bio NLP Workshop, “Improving Adverse Drug Event Extraction with Span BERT on different text typologies”, 2021

[6] Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., & Stoyanov, V., "ROBERT a: A Robustly Optimized BERT Pretraining Approach," ar Xiv preprint arXiv:1907.11692, 2019.

[7] Weissenbacher, D., et al., "Text Classification Models for the Automatic Detection of Nonmedical Prescription Medication Use from Social Media," Journal of the American Medical Informatics Association (JAMIA), vol. 28, no. 3, pp. 512–520, 2021.

[8] D.Weissenbacher ,” Text Classification Models for the Automatic Detection of Nonmedical Prescription Medication Use from Social Media”, Journal of American medical Informatics Association, 2021

[9] A. Fisher, M. Maclaren young, D. payer, K. Pacheco, C. Dubeau, and V. Mago, “Automating Detection of Drug-related harms on Social Media: Machine Learning Framework”, Journal of Medical Internet Research

[10] “Monitoring opioid-related Social Media chatter using natural language processing and large language models:” Temporal Analysis, “Journal of medical Internet research”, 2025

Share your valuable work from Social Media Buttons