• Ashrayuj Pandey
• Ankur Vishwakarma
• Abhishek Kumar
• Naveen Pal
• Anurag Gupta

The widespread adoption of online platforms by terrorist groups for recruitment, spreading propaganda, and planning attacks is one of the major risks to global security. This paper suggests a new multimodal framework utilizing artificial intelligence (AI) and machine learning (ML) to identify such activities in text, image, and network data modalities. By adopting transformer-based models to analyze text, convolutional neural networks (CNNs) for image recognition, and graph neural networks (GNNs) for user interaction analysis, our system demonstrates strong recall and robustness against adversarial strategies. Large-scale experiments confirm its effectiveness, while discussions of ethical considerations, scalability issues, and future directions—such as multi-lingual support and Explainability—point toward its enormous potential to revolutionize counter-terrorism operations in the digital era.

Terrorist activity detection, artificial intelligence (AI), machine learning (ML), multimodal analysis, online extremism, transformer models, convolutional neural networks (CNNs), graph neural networks (GNNs), online radicalization, propaganda detection, social media monitoring, adversarial robustness, text analysis, image recognition, user interaction analysis, hybrid models, counter-terrorism, real-time monitoring, cybersecurity, ethical considerations in AI.

"Detection of Terrorist Activities on Online Platforms Using AI and Machine Learning: A Multi-Modal Approach for Securing Cyberspace", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 5, page no.g782-g788, May-2025, Available :http://www.jetir.org/papers/JETIR2505779.pdf

"Detection of Terrorist Activities on Online Platforms Using AI and Machine Learning: A Multi-Modal Approach for Securing Cyberspace", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 5, page no. ppg782-g788, May-2025, Available at : http://www.jetir.org/papers/JETIR2505779.pdf