No abstract

Android smartphone ecosystem is inundated with innumerable applications mainly developed by third party contenders leading to high vulnerability of these devices. In addition, proliferation of smartphone usage along with their potential applications in diverse field entice malware community to develop new malwares to attack these devices. In order to overcome these issues, an android malware detection framework is proposed wherein an efficient multistage fusion approach is introduced. For this, a robust unified feature vector is created by fusion of transformed feature matrices corresponding to multi-cue using non-linear graph based cross-diffusion. Unified feature is further subjected to multiple classifiers to obtain their classification scores. Classifier scores are further optimally fused employing Dezert-Smarandache Theory (DSmT). Strength of suggested model is assessed both qualitatively and quantitatively by ten-fold cross-validation on the benchmarked datasets. On an average of outcome, we achieved detection accuracy of 98.97% and F-measure of 0.9936.

Android Smartphones are proliferating extensively in the digital world due to their widespread applications in a myriad of fields. The increased popularity of the android platform entices malware developers to design malicious apps to achieve their malevolent intents. Also, static analysis approaches fail to detect run-time behaviors of malicious apps. To address these issues, an optimal unification of static and dynamic features for smartphone security analysis is proposed. The proposed solution exploits both static and dynamic features for generating a highly distinct unified feature vector using graph based cross-diffusion strategy. Further, a unified feature is subjected to the fuzzy-based classification model to distinguish benign and malicious applications. The suggested framework is extensively experimentally validated through both qualitative and quantitative analysis and results are compared with the existing solutions. Performance evaluation over benchmarked datasets from Google Play Store, Drebin, Androzoo, AMD, and CICMalDroid2020 revealed that the suggested solution outperforms state-ofthe-art methods. We achieve average detection accuracy of 98.62% and F1 Score of 0.9916.

Android Operating system (OS) has grown into the most predominant smartphone platform due to its flexibility and open source characteristics. Because of its openness, it has become prone to numerous attackers and malware designers who are constantly trying to elicit confidential information by articulating a plethora of attacks through these designed malwares. Detection of these malwares to protect the smartphone is the core function of the smartphone security analysis. This paper proposes a novel traffic-based framework that exploits the network traffic features to detect these malwares. Here, a unified feature (UF) is created by graph-based cross-diffusion of generated order and sparse matrices corresponding to the network traffic features. Generated unified feature is then given to three classifiers to get corresponding classifier scores. The robustness of the suggested framework when evaluated on the standard datasets outperforms contemporary techniques to achieve an average accuracy of 98.74 per cent.