Tebite Ogonetejiri Andrew

Lancaster University Ghana | | Degree: Bsc. Computer Science
Artificial Intelligence models (techniques) used in detection of malware


Artificial models are becoming increasingly important in the detection of malware, as traditional signature-based approaches have become less effective in identifying new and emerging threats. Malware is a malicious software designed to disrupt or damage computer systems, and it can take various forms, including viruses, worms, and Trojans.

Machine learning algorithms, such as support vector machines, decision trees, and neural networks, have been applied to detect malware by analyzing its behavior or code. Behavioral-based approaches monitor the actions of software to identify suspicious behavior, while static analysis-based approaches analyze the code of the software to detect anomalies or malicious instructions.

Deep learning models, such as convolutional neural networks and recurrent neural networks, have shown promising results in detecting malware, particularly in the area of static analysis. These models can extract features from the software code and identify patterns that are indicative of malware.

In addition, hybrid approaches that combine multiple artificial models have been proposed to improve the accuracy of malware detection. These models can leverage the strengths of different techniques to provide a more comprehensive and effective detection system.

Overall, the use of artificial models in the detection of malware has shown great potential in improving the security of computer systems, and it is likely to become even more important in the future as new and more sophisticated forms of malware emerge.



Tebite Ogonetejiri Andrew