Malware is one of the most popular cyber-attacks, and it is becoming more common on the network every day. In contrast to benign transmission, which typically exhibits symmetrical patterns, malware communication often shows asymmetrical behaviours, making detection a complex challenge. Fortunately, malware can be distinguished and identified for actual activities utilizing a variety of artificial intelligence methods. However, insufficient work has been allocated to the problem of handling high-dimensional and huge data. This paper proposes a novel deep learning-based approach to identify malicious Uniform Resource Locators (URLs) specifically designed to handle the challenges posed by large-scale and complex data. Initially, input data is sourced from a comprehensive Kaggle dataset, which includes diverse and large-scale URL samples. The URLs are then transformed into vector representations using a Vector Embedding Module, which employs a character-level word embedding technique to capture intricate patterns within the URLs. To further refine the data, the Chaotic Kookaburra Efficient-Bo Network (CKEBO-Net) is applied to extract the most significant features from these vectors, effectively reducing the dimensionality and computational burden. Subsequently, the Cascaded Capsule Twin Attentional Dilated Convolutional Network (C~2TA_DiCN) model is introduced to classify and identify malicious URLs with high precision. This model leverages the unique strengths of capsule networks and attentional mechanisms, enhancing its capability to capture subtle dependencies within the data. Furthermore, the Lyrebird Meta-heuristic Optimization (LMO) algorithm is used to fine-tune the model parameters appropriately, ensuring that the training process is efficient and robust. The proposed approach is implemented using Python and rigorously evaluated on the Kaggle dataset. Simulation results demonstrate that the proposed method significantly outperforms existing models, achieving a malicious URL detection accuracy of 99.7%.
NETL
NSTL
Elsevier
