BOA-LSSVM Network-Based Malware Detection with Combination Weighting

With the rapid development of the internet, network malware such as viruses, worms, and trojans has become increasingly complex and covert, posing significant threats to information security for individuals, businesses, and nations. Traditional malware detection methods rely on feature signatures or rule-based systems, which struggle to address novel and unknown threats and are often bypassed. Technologies like machine learning are extensively used in cybersecurity for automating the detection of network malware and examining unsafe factors during internet usage. Addressing these issues, this paper proposes a BOA-LSSVM network malware detection method based on combination weighting, which leverages the advantages of optimization algorithms and machine learning. Experiments conducted on real-world datasets demonstrate that this method outperforms traditional approaches in terms of accuracy, precision, recall, and <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$F 1$</tex> score. The effectiveness of this method has been validated, providing an effective technological means to enhance network security. The results of this research are expected to significantly advance the field of cybersecurity.