boosting app clone detection efficiency through robust approach neural network application
AISHWARYA R,CATHERINE A,A. SUNITHA M.E.,
Published in International Journal of Advanced Research in Computer Science Engineering and Information Technology
ISSN: 2321-3337 Impact Factor:1.521 Volume:6 Issue:3 Year: 30 March,2021 Pages:1426-1431
Abstract
The scope of this project is to detect cloned Android app pairs but not to identify which is the original one and which is the cloned one. We only focus on the apps whose user interface features are defined in layout XML files. Apps with no or very few layout files, such as web apps, games based on third-party engines, and background apps with only services, are out of the scope of our paper. Just like previous static detection systems, apps whose user interface is dynamically defined by programs are also out of the scope of our paper. All of the apps used in our evaluation are not paid apps, so we can crawl enough apps to simulate the real-world scenario. The description of an app on the third-party market may be missing or not match the apps implementation. Although the consistent description is not essential in our detection system, it can greatly improve our detection speed. Hence, apps with inconsistent description will increase the time complexity of our method. Our paper does not concern these apps, because (a) this kind of app arouses the vigilance of users very easily and (b) the inspection by the app market is becoming more and more strict.
Kewords
ANN – Artificial Neural Network, CFG – Control Flow Graph, SDK – Software Development Kit.
Reference
1. M. Sun, M. Li, and J. C.S. Lui, “DroidEagle: Seamless detection of visually similar Android apps,” in Proceedings of the 8th ACM Conference on Security & Privacy in Wireless and Mobile Networks, 2015, pp. 9 2. L. Li, T. F. Bissyandé, and J. Klein, “SimiDroid: Identifying and explaining similarities in Android apps,” in IEEE Trustcom/BigDataSE/ICESS, 2017, pp. 136-143. 3. H. Wang, Y. Guo, Z. Ma, and X. Chen, "WuKong: a scalable and accurate two- phase approach to Android app clone detection," in Proceedings of the 2015 International Symposium on Software Testing and Analysis, ACM, 2015, pp. 71- 82 4. Yang W, Zhang Y, Li J, et al. AppSpear: Bytecode Decrypting and DEX Reassembling for Packed Android Malware[M]//Research in Attacks, Intrusions, and Defences. Springer International Publishing, 2015: 359- 381.
