Copyright © 2026 Authors retain the copyright of this article. This article 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.

@article{193809,
        author = {Nambiraj. S and Adhith K.R and Maadhula R},
        title = {AI-Based Cybercrime Detection on Social Media: Fake Profile and Cyberbullying Identification Using Machine Learning and NLP with Malware Forensic Analysis for Attack Source Attribution},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {10},
        pages = {1820-1823},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=193809},
        abstract = {The rapid growth of social media platforms has significantly transformed communication, networking, and information sharing across the world. However, the widespread adoption of these platforms has also resulted in the rise of cybercrime activities such as fake profiles, cyberbullying, identity theft, harassment, and coordinated online attacks. Traditional rule-based security systems are often insufficient to handle the complexity and scale of modern cyber threats. Artificial Intelligence (AI), particularly Machine Learning (ML) and Natural Language Processing (NLP), has emerged as an effective solution for detecting and mitigating cybercrime on social media platforms. This study explores an integrated AI-based framework for cybercrime detection focusing on three major aspects: identification of fake social media profiles, detection of cyberbullying using NLP-based sentiment and linguistic analysis, and malware forensic analysis for identifying the source of cyber attacks. Machine learning algorithms such as Random Forest, Support Vector Machine, and Decision Trees are applied to classify suspicious user behaviors and detect malicious patterns in user interactions. NLP techniques including text classification, sentiment analysis, and semantic analysis are used to identify abusive language and harmful online communication. Additionally, malware forensic techniques are integrated into the framework to analyze malicious scripts and digital traces that help attribute attacks to their origin. The proposed system aims to enhance the security of social media environments by enabling proactive detection and prevention of cyber threats. The research demonstrates that combining machine learning, NLP, and digital forensic analysis significantly improves detection accuracy and provides reliable mechanisms for identifying the perpetrators of cybercrime. This approach can support law enforcement agencies, cybersecurity professionals, and social media platforms in combating cybercrime and protecting users from online harm.},
        keywords = {Cybercrime detection, Artificial Intelligence, Machine Learning, Natural Language Processing.},
        month = {March},
        }