AI-Powered Defence: Leveraging Deep Learning for Effective Malware Detection

In an era where cyber threats are increasingly sophisticated, traditional malware detection methods often fall short in identifying and mitigating malicious activities. Malicious software is defined as any software that gains access to a computer system without the authorization of administrators. This paper utilized a combination of Machine learning and deep learning techniques in enhancing malware detection systems, presenting a comprehensive framework for leveraging artificial intelligence to improve cybersecurity defenses. A groundbreaking deep learning system has been created to combat the rising number of malicious programs. Findings from malware analysis and detection, along with machine learning techniques for calculating the difference in correlation symmetry, enabled the detection of harmful traffic on computer systems, improving network security significantly. The results by analyzing and detecting malware using machine and deep learning algorithms such as: (Logistic Regression (LR), Extra Trees, K-Nearest Neighbors (KNN), Naive Bayes (NB), Support Vector Machine (SVM), TabNet, Artificial Neural Networks (ANN) and Long Short Term Memory (LSTM)) to determine which one is most accurate for malware detection. The findings indicated that in comparison to other classifiers, sequential model accuracy: (99.98%), ANN (95.7%), TabNet (95.1%), and LR (95.8%), Extra Trees (95.5%), SVM (95.7%), NB (91.3%) performed well in terms of detection accuracy in a given dataset were compared. Considering the sophistication and prevalence of malicious software, these discoveries are substantial.