Exécution de notre outil de synthèse sur un nouvel article
Vérifiez l’article ci-dessous, puis lancez sa synthèse.
ATTENTION-DRIVEN TABULAR DEEP LEARNING FRAMEWORK FOR DETECTING FAKE PROFILES IN SOCIAL NETWORKING PLATFORMS
Suba Suba, S. Geetha, S. Prabakaran, P. Anbumani, S. Gunasekaran, Balasowmiya D
Résumé : Background The quick development of the social networking sites has brought about more opportunities in communication and exchange of information, but it has also enhanced the existence of fake user accounts that indulge in activities like spamming, spreading misinformation and fraud over the internet. Such bad actors can pose a massive credibility and security risk to social media ecosystems. As such, the issue of coming up with effective and scalable systems of detecting the fraud profiles has now been a significant research question. Objective The paper describes a deep learning model of attention-based tabular detection of fake profiles in social networking platforms. Materials and Methods The given solution uses the TabNet architecture which is a deep learning system that is explicitly adapted to structured tabular data and that uses a sequential attention system that determines the most relevant features in the course of the learning process. The framework incorporates several types of user data, such as profile attributes, pattern of behavioral activities, network interactions feature, and metadata of user accounts. The model can extract the complex relationships in the dataset even though the decision-making process can be interpreted since it is automatic and the model focuses on the most informative characteristics. Results Experimental analysis of a labeled dataset of real and fake accounts proves that the suggested framework yields high classification results, which are measured in accuracy, precision, recall, and F1-score. Conclusion These findings suggest that attention-based tabular learning can offer a scalable and efficient solution to automated fake profile detection on the current social networking systems.