Intensifying Cross Architecture Cyber-Resilience System with Descriptive Malware Analysis

Cyberthreat landscapes are constantly evolving, requiring flexible but robust cyber-resilience architectures across various systems. Through descriptive malware analysis, this work presents an inclusive methodology to strengthen cyber-resilience. The method involves dataset collection and feature selection initially. After preprocessing and fine-tuning, synthetic malware samples are generated and integrated with malware and benign samples to train machine learning methods such as support vector machines, logistic regression, and LSTM with their optimizers. The efficiency of the model is enhanced by integrating the predictions of the models with each other using the soft voting technique and the ensemble model is thus achieved, By strengthening the system’s ability to adapt to new threats, this technique increases our understanding and helps in detecting known and unknown risks.