Using Static and Dynamic Malware features to perform Malware Ascription

Malware ascription is a relatively unexplored area, and it rather difficult to attribute malware detect authorship. In this paper, we employ various Static Dynamic features of malicious executables classify based on their family. We leverage Cuckoo Sandbox machine learning make progress in research. Post analysis, classification performed using deep algorithms. Using the gathered from VirusTotal (static) (dynamic) reports, ran vectorized data against Multinomial Naive Bayes, Support Vector Machine, Bagging Decision Trees as base estimator. For each classifier, tuned hyper-parameters exhaustive search methods. Our reports can be extremely useful ascription.