Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.
Chapter 19 explores how AI, particularly deep learning models like RNNs and CNNs, enhances malware detection by analyzing static and dynamic features, addressing the growing complexity of cyber threats with automated precision.
In this section, we present published research on deep neural networks and malware detection.
Chevron 3 steps5 questions
Section 19.3 presents a proposed method for malware detection, which integrates both static and dynamic analysis by extracting features from PE files, processing API call sequences with RNNs, transforming combined data into images, and classifying them using CNNs
Chevron 5 steps5 questions
Section 19.4 presents the experiment and evaluation of the proposed malware detection model, detailing the dataset collection from sources like VirusShare and Maltrieve, the use of Cuckoo sandbox for extracting API call sequences, and the 3-fold cross-validation method applied to assess the model’s performance.
Chevron 4 steps5 questions
Get personalized course recommendations, track subjects and courses with reminders, and more.
