Malicious URL Classification Using Artificial Fish Swarm Optimization and Deep Learning

Cybersecurity-related solutions have become familiar since it ensures security and privacy against cyberattacks in this digital era. Malicious Uniform Resource Locators (URLs) can be embedded email or Twitter used to lure vulnerable internet users implement malicious data their systems. This may result compromised of the systems, scams, other such cyberattacks. These attacks hijack huge quantities available data, incurring heavy financial loss. At same time, Machine Learning (ML) Deep (DL) models paved way for designing that detect URLs accurately classify them. With motivation, current article develops an Artificial Fish Swarm Algorithm (AFSA) with Enabled URL Detection Classification (AFSADL-MURLC) model. The presented AFSADL-MURLC model intends differentiate from genuine URLs. To attain this, initially carries out preprocessing makes use glove-based word embedding technique. In addition, created vector is then passed onto Gated Recurrent Unit (GRU) classification recognize Finally, AFSA applied proposed enhance efficiency GRU technique was experimentally validated using benchmark dataset sourced Kaggle repository. simulation results confirmed supremacy over recent approaches under distinct measures.