一句话：提出将 Dalvik 字节码转化为图像并用 CNN 检测 Android 恶意软件的方法，检测时间 0.22 秒、准确率超 93%。
针对 Android 恶意软件数量庞大、且现有检测技术面临数据混淆和代码覆盖率有限等问题，本文提出一种图像启发、基于 CNN 的检测方法。该方法直接从 Dalvik 字节码中学习恶意软件特征，利用深度学习自动提取判别信息，避免传统方法对人工特征或完整程序覆盖的依赖。评估表明，模型平均检测时间为 0.22 秒，显著低于现有方法，整体准确率超过 93%。
Until 2017, Android smartphones occupied approximately 87% of the smartphone market. The vast market also promotes the development of Android malware. Nowadays, the number of malware targeting Android devices found daily is more than 38,000. With the rapid progress of mobile application programming and anti-reverse-engineering techniques, it is harder to detect all kinds of malware. To address challenges in existing detection techniques, such as data obfuscation and limited code coverage, we propose a detection approach that directly learns features of malware from Dalvik bytecode based on deep learning technique (CNN). The average detection time of our model is0.22 seconds, which is much lower than other existing detection approaches. In the meantime, the overall accuracy of our model achieves over 93%.
DOI 原文 ·
@inproceedings{paperbot5317,
title = {An Image-Inspired and CNN-Based Android Malware Detection Approach},
author = {Xusheng Xiao and Shao Yang},
booktitle = {ASE},
year = {2019},
doi = {10.1109/ase.2019.00155}
}