• K. Nishitha
• G.Rajesh
• N.Haritha

The current trend shows a significant increase in the popularity of smart phone operating systems. However, this rise has also made them a prime target for hackers and attackers, particularly in the case of Android applications. As a result, there has been a noticeable surge in malicious code attacks on the Android platform, making it an appealing target for such perpetrators. These malevolent actors have developed sophisticated techniques to hide harmful algorithms within seemingly innocent Android applications, posing a challenge for security firms in identifying and classifying these apps as malware. Android malware has evolved to evade traditional detection methods due to its increasingly unique characteristics. Machine learning-based techniques have emerged as a more effective solution for addressing the complex challenge of emerging Android threats. These approaches analyze the behaviors exhibited by existing malware patterns and leverage this data to differentiate between known threats and novel risks.This study proposes a novel approach to identifying weaknesses in mobile apps. The key contributions are twofold:First, the study presents a model that combines more innovative feature sets with the largest existing malware sample records, going beyond traditional methods. Second, the model employs ensemble learning with machine learning algorithms such as AdaBoost and SVM to enhance its accuracy and performance.The test results demonstrate that the proposed model achieves a 96.24% accuracy rate in identifying malware samples from Android apps, with a low 0.3 false positive rate. Crucially, the model incorporates overlooked malicious features such as permissions, targets, and API calls, and is trained using a single reverse-engineered sample as input.Overall, this study offers a significant advancement in mobile app security, providing a robust and comprehensive solution for detecting malware.

Machine Learning, Cyber Security, ,Malware

"UTILIZING MACHINE LEARNING-BASED REVERSE ENGINEERING TECHNIQUES TO IDENTIFY MALWARE ON MOBILE DEVICES WITHIN ANDROID APPLICATIONS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 6, page no.h223-h232, June-2024, Available :http://www.jetir.org/papers/JETIR2406724.pdf

"UTILIZING MACHINE LEARNING-BASED REVERSE ENGINEERING TECHNIQUES TO IDENTIFY MALWARE ON MOBILE DEVICES WITHIN ANDROID APPLICATIONS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 6, page no. pph223-h232, June-2024, Available at : http://www.jetir.org/papers/JETIR2406724.pdf