International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 10 Issue: 04 | Apr 2023
p-ISSN: 2395-0072
www.irjet.net
Android Malware Detection Aasthaa Bohra1, Gayatri Shahane2, Sakshi Shelke3, Dr. Shalu Chopra4 1,2,3INFORMATION TECHNOLOGY VESIT(of Mumbai University) Mumbai, India 4INFORMATION TECHNOLOGY, HOD VESIT(of Mumbai University) Mumbai, India
---------------------------------------------------------------------------***-----------------------------------------------------------------system. It can take the form of viruses, worms, trojans, Abstract — Android malware detection involves
ransomware, spyware, adware, and others. Malware can infect a computer by exploiting security vulnerabilities, tricking the user into installing it, or through phishing attacks. Its effects can range from annoying pop-up ads to serious data theft or destruction. To protect against malware, it is recommended to keep your operating system and software up to date, use a reliable antivirus program, be cautious of email attachments and links, and use strong passwords.
identifying malicious software on Android devices. This can be accomplished through various techniques such as signature-based detection and behavior-based detection. However, these techniques cannot detect unknown malware. Hence, we have used machine learning algorithms for malware detection. Machine learning-based malware detection uses algorithms to identify patterns and behaviors characteristic of malware, without relying on previously known signatures. This type of detection can be more effective in detecting unknown or evolving threats. It involves training machine learning models on large datasets of both benign and malicious software to identify common features. During runtime, the trained model is then applied to incoming files to determine if they contain malware. This type of detection is becoming increasingly popular due to its ability to adapt to new threats in real-time. Machine learning-based malware detection involves using algorithms to automatically identify and classify malicious software based on patterns and behaviors. This can include supervised learning, where a model is trained on a dataset of labeled malware and benign samples. These methods have shown promising results in detecting previously unseen and evolving malware threats. However, they can also be prone to false positive and false negative errors, and it is important to properly validate and test models before deploying them in production environments. Malware detection using machine learning involves training a machine learning model on a large dataset of benign and malicious software to identify patterns and behaviors associated with malware. The model can then be used to analyze new, unknown software and determine if it is malicious or benign. Some commonly used machine learning algorithms for malware detection include decision trees, random forests, and neural networks.
Proliferation of mobile devices has led to an increase in the number of android malware cases. Various antimalware detection programs have been built to tackle these issues. Signature-based detection is a method for detecting Android malware by comparing the code of an Android application against a database of known malware signatures. If a match is found, the application is flagged as malicious. This method is fast and reliable, but it only detects known malware, and new or unknown threats will not be detected. To improve the detection rate, signature-based detection is often combined with other methods such as behavioral analysis. Behavioral analysis is a method for detecting malware by observing the behavior of an application during its execution. This approach looks at how the application interacts with the operating system, network resources, and other applications, and checks for any unusual or malicious behavior. This method is more effective at detecting unknown or new malware, but it is also more resourceintensive and slower than signature-based detection. By combining behavioral analysis with signature-based detection, the overall accuracy of detecting malware can be improved. Machine learning-based Android malware detection is a method for detecting malicious files by using machine learning algorithms. These algorithms are trained on large datasets of known malware and benign files, and then use this training to identify new apps as malicious or benign. This method can be more effective at detecting unknown or new malware, as it can identify patterns and relationships in the data that may not be immediately apparent. Additionally, machine learning algorithms can continually learn and adapt to new threats, improving their accuracy over time. Non-signature-based detection totally eliminates the attack window time and can also detect unknown, zero-day and modern malware which
Keywords—Android, Malware, Machine learningbased, Detection
I. INTRODUCTION Malware is short for malicious software, refers to any program or code designed to harm or exploit a computer
© 2023, IRJET
|
Impact Factor value: 8.226
|
ISO 9001:2008 Certified Journal
|
Page 1183