The field of cybersecurity is moving towards the development of more advanced and efficient threat detection and prevention systems. Researchers are exploring the use of graph neural networks, attention mechanisms, and federated learning to improve the accuracy and scalability of these systems. Notable advancements include the use of graph-based models to detect malicious URLs and predict credential stuffing risks, as well as the development of transparent and interpretable methods for quishing detection. Noteworthy papers include: A Graph-Attentive LSTM Model for Malicious URL Detection, which achieved outstanding performance with a test accuracy of 0.9806 and a weighted F1-score of 0.9804. PassREfinder-FL, a novel framework that predicts credential stuffing risks across websites, achieving an F1-score of 0.9153 in the federated learning setting.