The datasets are listed are taken from various previous research approaches. A variety of machine learning techniques are also identified and categorized in different classes. Various hybrid methods are analyzed and mapped according to the combination of static and dynamic features used. Furthermore, features used in static and dynamic technique are classified according to their usage in recent approaches. The different techniques which are used to investigate malicious application are identified. In this, 380 research articles are studied which are published in various prominent international journals and conferences. Standard systematic literature review method is used to carry out the research. The objective of study is to report a systematic literature review regarding malicious application detection in android operating system. Therefore, attackers are developing new techniques to steal the data from smartphones. Unfortunately, data related to privacy is center of attraction for attackers. People are using new technologies and storing prominent data in their smartphones. In last decade, due to tremendous usage of smart phones it seems that these gadgets became an essential necessity of day-to-day life. The results of our experimentations show that our filtering and abstraction process has positive impacts on the performance and the accuracy of the selected malware detection approach. It represents the last line of defense of an in-depth protection strategy for smartphone systems. This model is based on the 200 most popular free Android applications available in the Android market. This process is used to build a database describing a canonical normal behavior model of Android applications. To achieve this goal, we introduce a filtering and abstraction process, which (i) removes irrelevant system calls to describe the main behavior of an Android application and (ii) unifies system calls having the same functionality but different names. In this paper, we revisit a classical anomaly-based malware detection approach (i.e., database of normal behavior) analyzing Android system calls with two conflicting objectives: reducing the time and space complexities of the selected approach without decreasing its accuracy performance. These factors have major impacts on the accuracy performance of the detection techniques as well as on their time and space complexities. Most of these efforts have focused on the dataset available for analysis and/or the algorithms used to distinguish between normal or abnormal behavior. Improving anomaly-based malware detection techniques has been widely studied in recent years. In our evaluations, we correctly identify 333 out of 354 security-sensitive behaviors, achieving 96.43% precision and 91.53% recall, the experimental result demonstrates that our approach can effectively and accurately detect and block malicious behaviors of Android apps. ![]() Finally, an approach using user intention features is proposed to differentiate benign and malicious behaviors. Then the user intention features, which can perceive the correlations between user intention and app behavior from time, process, semantic and data perspectives, are extracted from the records obtained by IBdroid. Based on this discovery, we first design and realize IBdroid, which can precisely monitor user inter-faces, user actions and security-sensitive behaviors of apps. The user knows and wants this behavior to happen. We propose that a fundamental difference between malicious and benign behaviors is that their corresponding user intentions are different, i.e., whether there is an association between the app behavior and user intention. Security-sensitive behaviors in Android applications (apps for short) may or may not be malicious.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |