Artificial intelligence-driven cybersecurity: enhancing malicious domain detection using attention-based deep learning model with optimization algorithms

Malicious domains are one of the main resources mandatory for adversaries to run attacks over the Internet. Owing to the significant part of the domain name system (DNS), detailed research has been performed to detect malicious fields according to their unique behaviour, which is considered in dissimilar stages of the DNS life cycle queries and explanations. The DNS has played a crucial role in the evolution of the Internet. Its primary objective is to simplify user experience by converting a website's Internet Protocol (IP) address into a recognizable domain name and vice versa. Identifying these adverse fields is meaningful in contesting increased network attacks. Artificial intelligence (AI) is applied to develop the areas of malicious domain recognition and hindrance by the probability to improve robust, efficient, and scalable malware detection units. AI methods have expressed significant results in malicious domain detection. This manuscript presents an Enhance Malicious Domain Detection Using an Attention-Based Deep Learning Model with Optimization Algorithms (EMDD-ADLMOA) technique. The proposed EMDD-ADLMOA technique relies on improving malicious domain detection in cybersecurity. Initially, the min-max scaling method is utilized in the pre-processing phase to convert input data into an appropriate design. For feature selection (FS), the proposed EMDD-ADLMOA technique utilizes the quantum-inspired firefly algorithm (QIFA) model. Furthermore, the hybrid model of a temporal convolutional network and bi-directional long short-term memory with squeeze-and-excitation Attention (TCN-BiLSTM-SEA) model is employed for the classification process. Finally, the parrot optimization (PO) model optimally fine-tunes the hyperparameter values of the TCN-BiLSTM-SEA model. The performance results of the EMDD-ADLMOA approach are verified under a malicious dataset. The experimental validation of the EMDD-ADLMOA approach portrayed a superior accuracy value of 98.52% over existing techniques.