Exploiting smartphone defence: a novel adversarial malware dataset and approach for adversarial malware detection

Adversarial malware poses novel threats to smart devices since they grow progressively integrated into daily life, highlighting their potential weaknesses and importance. Several Machine Learning (ML) based methods, such as Intrusion Detection Systems (IDSs), Malware Detection Systems (MDSs), and Device Identification Systems (DISs), have been used in smart device security to detect and prevent cyber-attacks. However, ML still has much malware to overcome, including the proliferation of adversarial malware designed to deceive classifiers. This research generates two novel datasets: first by injecting adversarial attacks in binary malware detection dataset named ADD-1 and second by injecting attacks in malware category detection dataset named ADD-2. Further, it provides an approach to detect adversarial static malware in smartphones utilizing different ML models (Random Forest (RF), Extreme Gradient Boosting (XGB), Decision Tree (DT) and Gradient Boosting (GB), ensemble voting, and Deep Neural Network (DNN) models. This study preprocessed data by analyzing and converting the categorical data into numerical values using the data normalization technique (i.e., standard scalar). According to the findings, the proposed XGB model predicts adversarial attacks with 88% accuracy and outperforms conventional ML and DL models.