Developing Adversary-Aware Classifiers for Android Malware Detection

开发用于 Android 恶意软件检测的对手感知分类器

• 批准号: DP200100886
• 负责人: Prof Yang Xiang
• 金额: $ 29.49万
• 依托单位: Swinburne University of Technology
• 依托单位国家: 澳大利亚
• 项目类别: Discovery Projects
• 财政年份: 2020
• 资助国家: 澳大利亚
• 起止时间: 2020-01-01 至 2024-12-31
• 项目状态: 已结题
• 来源: https://dataportal.arc.gov.au/RGS/Web/Grants/DP200100886
• 关键词: Developing; Adversary; Aware; Classifiers; Android

Smartphones have become increasingly ubiquitous in people’s everyday life. However, it was reported that one in every five Android applications were actually malware, considering that Android has taken 88% market share of mobile phones. As an effective technique, machine learning has been widely adopted to detect Android malware. However, recent work suggests that deliberately-crafted malware makes machine learning ineffective. In this project, we propose to develop a series of new techniques, such as 1) Android contextual analysis, 2) wrapper-based hill climbing algorithm, and 3) ensemble learning, to solve this problem. The outcomes will help Australia gain cutting edge technologies in adversarial machine learning and mobile security.

智能手机在人们的日常生活中越来越无处不在。但是，据报道，考虑到Android已在移动电话中占有88％的市场份额，实际上每五个Android应用程序实际上是恶意软件。作为一种有效的技术，机器学习已被广​​泛采用以检测Android恶意软件。但是，最近的工作表明，故意制作的恶意软件使机器学习无效。在这个项目中，我们建议开发一系列新技术，例如1）Android上下文分析，2）基于包装的山坡攀岩算法和3）整体学习，以解决此问题。这些结果将有助于澳大利亚在对抗机器学习和移动安全性方面获得尖端技术。