Abstract: Social media sites such as Facebook, Instagram, blogs, and Twitter have become the most popular places for people of all ages to spend much of their time because they allow users to share information rapidly and broadly, which in turn attracts new users. The huge rise in daily visitors to these sites is increasing the risk of giving false information and becoming a victim of fraudulent accounts. A phoney account is frequently used to spread misleading information, send spam, forward phishing attack URLs, and steal contacts for personal benefit or the detriment of competitors. Therefore, Finding fraudulent users and spammers on online social networks (OSNs) is a popular research topic.

This study examined the effects of fake profiles and new methods for identifying them, including deep learning and machine learning algorithms like Support Vector Machine (SVM), Logistic Regression (LR), Random Forest (RF), and K-Nearest Neighbours (KNN). A comparison of different techniques for cross-platform profile verification or re-identification is also provided in order to mitigate the harm caused by fraudulent profiles.

Keywords: Cross-platform identification, online social media networks, profile cloning, fake profiles, and profile re-identification.

Downloads: | DOI: 10.17148/IARJSET.2026.13141