Malware detectors based on machine learning are vulnerable to adversarial attacks. Generative Adversarial Networks (GAN) are architectures based on Neural Networks that could produce successful adversarial samples. The interest towards this technology is quickly growing. In this paper, we propose a system that produces a feature vector for making an Android malware strongly evasive and then modify the malicious program accordingly. Such a system could have a twofold contribution: it could be used to generate datasets to validate systems for detecting GAN-based malware and to enlarge the training and testing dataset for making more robust malware classifiers.
翻译:基于机器学习的恶意探测器很容易受到对抗性攻击。 生成反反向网络(GAN)是建立在神经网络基础上的建筑,可以产生成功的对抗性样本。 对这项技术的兴趣正在迅速增长。 在本文中,我们建议建立一个系统,产生一种特性矢量,使Android恶意软件能进行强烈的规避,然后相应修改恶意程序。 这样一个系统可以有双重贡献:它可用于生成数据集,以验证检测基于GAN的恶意软件的系统,并扩大培训和测试数据集,使恶意软件分类更加强大。