Decoding the Secrets of Machine Learning in Malware Classification: A Deep Dive into Datasets, Feature Extraction, and Model Performance

Many studies have proposed machine-learning (ML) models for malware detection and classification, reporting an almost-perfect performance. However, they assemble ground-truth in different ways, use diverse static- and dynamic-analysis techniques for feature extraction, and even differ on what they consider a malware family. As a consequence, our community still lacks an understanding of malware classification results: whether they are tied to the nature and distribution of the collected dataset, to what extent the number of families and samples in the training dataset influence performance, and how well static and dynamic features complement each other. This work sheds light on those open questions. by investigating the key factors influencing ML-based malware detection and classification. For this, we collect the largest balanced malware dataset so far with 67K samples from 670 families (100 samples each), and train state-of-the-art models for malware detection and family classification using our dataset. Our results reveal that static features perform better than dynamic features, and that combining both only provides marginal improvement over static features. We discover no correlation between packing and classification accuracy, and that missing behaviors in dynamically-extracted features highly penalize their performance. We also demonstrate how a larger number of families to classify make the classification harder, while a higher number of samples per family increases accuracy. Finally, we find that models trained on a uniform distribution of samples per family better generalize on unseen data.

Malware Traffic Classification: Evaluation of Algorithms and an Automated Ground-truth Generation Pipeline

Identifying threats in a network traffic flow which is encrypted is uniquely challenging. On one hand it is extremely difficult to simply decrypt the traffic due to modern encryption algorithms. On the other hand, passing such an encrypted stream through pattern matching algorithms is useless because encryption ensures there aren't any. Moreover, evaluating such models is also difficult due to lack of labeled benign and malware datasets. Other approaches have tried to tackle this problem by employing observable meta-data gathered from the flow. We try to augment this approach by extending it to a semi-supervised malware classification pipeline using these observable meta-data. To this end, we explore and test different kind of clustering approaches which make use of unique and diverse set of features extracted from this observable meta-data. We also, propose an automated packet data-labeling pipeline to generate ground-truth data which can serve as a base-line to evaluate the classifiers mentioned above in particular, or any other detection model in general.