• Sagar Raj Patil
• Rajni Ranjan Singh Makwana

Recently, the adoption, as well as usage of smartphones, have risen, making them the primary mode of communication. The majority of Android smartphone applications, or software, are free; but, to earn income, adverts are shown while an app is being accessed. Through numerous types of malware attacks, such as Advertising Software (Adware), attackers are continually watching cellphones to get confidential relevant data from users. Every year, billions of dollars are wasted as a result of adware conducting advertising frauds. Machine learning (ML) approaches are being investigated by security experts and scholars to improve the identification of Android malware. In this research, a novel detection model for protecting smart devices against adware assaults is described, which monitors network traffic to do so. Numerous data pre-processing approaches, feature selection methods, & machine learning techniques are utilized to find adware examples in the dataset that is being provided. Two machine learning techniques, including Dynamic random forest and Split-Point & Attribute Reduced Classifier or SPAARC tree, are employed. Weka is being utilized to preprocess data using Information Gain (IG) & to do ML operations on data. As part of our research, we tested if the SPAARC tree method, when implemented to adware detection systems built on Android, was successful in pattern recognition procedure. The outcomes of the experiments proved that the adoption of the SPAARC tree method outperformed the classic Dynamic Random Forest approach in terms of accuracy in identifying adware attacks, with 95.16 percent accuracy. It identifies a 97.7% true positive rate for benign class 87.4% true positive for adware (adware) class. From this found that, ironically, the binary adware classification problem is easier to solve.

Android, Adware Detection, Machine Learning, SPAARC, Dynamic Random Forest.

"Android Platform Based Malicious Adware Detection Using SPAARC Tree ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 4, page no.f431-f443, April-2022, Available :http://www.jetir.org/papers/JETIR2204555.pdf

"Android Platform Based Malicious Adware Detection Using SPAARC Tree ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 4, page no. ppf431-f443, April-2022, Available at : http://www.jetir.org/papers/JETIR2204555.pdf