Anonymous Detect: A Machine Learning Model for Detecting Fake Profile on Instagram

Fraudulent profiles are constant threats in the security landscape of social media, thus, the extent to which they affect privacy and trustworthiness of information is dire. Conventional detection algorithm, like the heuristic or fixed rules models, is becoming ineffective due to the manoeuvres of malicious parties. Our model is called AnonymousDetect, and it is a machine learning algorithm that can be used to detect fake Instagram accounts. The gist of the system is an optimized XGBoost classifier that is trained on a well-designed profile attributes. In order to solve the typical problem of high profile dataset imbalance between classes, we use the Synthetic Minority Over-sampling Technique (SMOTE) to create a balanced and bias-free training regime. The performance of the anonymousDetect was strictly assessed and the accuracy of the classification was 93.4.