Scholarlink

Modern smartphones, with their advanced computing power, face significant security and privacy issues due to third-party applications. Android, as the most popular operating system, is increasingly targeted by hackers. With 4.9 billion people online in 2021 and an expected 7.7 billion smartphone subscriptions by 2028, the proliferation of Android devices has led to a rise in malware. Despite ongoing research and various detection methods, no solution is completely effective. This paper reviews dynamic analysis techniques, including machine learning and deep learning classifiers, for detecting malware during runtime, and also explores static, hybrid, permission-based, and emulation-based detection methods.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A Survey on Mobile Malware Detection Using Dynamic Techniques

  • 章节

  • 发表日期：

    2025年

查看全文
  • Chanchal Sharma,
  • Hemraj Shobharam Lamkuche,
  • Emma Qumsiyeh,
  • Ala’a Al Sherideh

摘要

Modern smartphones, with their advanced computing power, face significant security and privacy issues due to third-party applications. Android, as the most popular operating system, is increasingly targeted by hackers. With 4.9 billion people online in 2021 and an expected 7.7 billion smartphone subscriptions by 2028, the proliferation of Android devices has led to a rise in malware. Despite ongoing research and various detection methods, no solution is completely effective. This paper reviews dynamic analysis techniques, including machine learning and deep learning classifiers, for detecting malware during runtime, and also explores static, hybrid, permission-based, and emulation-based detection methods.