Enhancing Online Security: Detection of Fake Profiles on Instagram Using GBM

The rise of fake profiles on Instagram poses a significant threat to online security, leading to privacy breaches, misinformation, and fraudulent activities. Existing detection methods often suffer from low accuracy and struggle to adapt to evolving fraudulent techniques, highlighting the need for a more robust solution. This research addresses this gap by leveraging Gradient Boosting Machine (GBM) to detect fake profiles based on key features such as engagement metrics, profile activity, and authenticity indicators. A dataset of real and fake profiles is collected and pre-processed, followed by the implementation of GBM for classification. Experimental results demonstrate that GBM outperforms traditional machine learning models in terms of accuracy, precision, and recall. The findings highlight the potential of GBM in strengthening online security by minimizing fake account proliferation. Future work will explore deep learning models and real-time detection approaches to further enhance accuracy and adaptability.