An Optimized Intelligent Malware Detection Framework for Securing Digital Data

Digital data security has grown rapidly based on the advances of smart applications. Hence, the data is secured in several ways, like malicious prediction, avoidance, etc. However, classifying and preventing malicious actions is difficult because some malicious actions behave like normal users. When the data is entered, it captures it and does malicious activities. So, the current article was planned to build a novel chimp (You-Only-Look-Once) YOLO Malicious Avoidance Framework (CbYMAF) as the attack recognition and prevention mechanism. Here, the data was initialized in the primary stage, and then the noise constraints were neglected through the pre-processing function. Henceforth, the features are extracted, and the malicious actions are recognized. Finally, the malicious types were categorized, and the prevention module's features were updated to prevent malicious events. Besides, the unknown attack was launched to value the designed approach's confidentiality ratio. Finally, the Python framework validates the novel CbYMAF, and the comparative analysis is conducted with past works.