ISeCure The ISC Int'l Journal of Information Security November 2022, Volume 14, Number 3 (pp. 81–92) http://www.isecure-journal.org Presented at the ISCISC’2022 in Rasht, Iran. Lightweight Identification of Android Malware with Knowledge Distillation and Deep Learning Approach ✩ Somayeh Mozafari 1 , and Amir Jalaly Bidgoly 1,* 1 Department of Electrical and Computer Engineering, University of Qom, Qom, Iran. ARTICLE I N F O. Keywords: Android, Deep Learning, Ensemble Learning, Knowledge Distillation, Lightning, Malware Detection Type: Research Article doi: 10.22042/isecure.2022.14.3.9 dor: 20.1001.1.20082045.2022.14.3. 9.3 ABSTRACT Today, with the advancement of science and technology, the use of smartphones has become very common, and the Android operating system has been able to gain lots of popularity in the meantime. However, these devices face many security challenges, including malware. Malware may cause many problems in both the security and privacy of users. So far, the state-of-the-art method in malware detection is based on deep learning, however, this approach requires a lot of computing resources and leads to high battery usage, which is unacceptable in smartphone devices. This paper proposes the knowledge distillation approach for lightening android malware detection. To this end, first, a heavy model is taught and then with the knowledge distillation approach, its knowledge is transferred to a light model called student. To simplify the learning process, soft labels are used here. The resulting model, although slightly less accurate in identification, has a much smaller size than the heavier model. Moreover, ensemble learning was proposed to recover the dropped accuracy. We have tested the proposed approach on CISC datasets including dynamic and static features, and the results show that the proposed method is not only able to lighten the model up to 99%, but also maintain the accuracy of the lightened model to the extent of the heavy model. © 2022 ISC. All rights reserved. 1 Introduction T he Android operating system has become the first choice for many smartphone companies. About 86.6% of the phones that were sold in 2019 used the Android operating system [1]. Research has shown that by the end of 2020, there were about 2.8 mil- * Corresponding author. ✩ The ISCISC’2022 program committee effort is highly ac- knowledged for reviewing this paper. Email addresses: s.mozafarih@gmail.com, jalaly@qom.ac.ir ISSN: 2008-2045 © 2022 ISC. All rights reserved. lion apps in the official Google Stores. On the other hand, some issues led to security threats in mobile devices such as open source, request permissions at the installation time, and the lack of user awareness. According to published statistics, in 2018, the total number of known malicious apps was approaching 100 million. By the end of June 2018, the number of all known malicious apps had totaled 94.2 million and, on average, mobile malware is detected every 10 sec- onds. Due to the growing volume of Android malware, security solutions should be provided to reduce the damage to mobile phones and maintain user security. ISeCure