AI methods have been proven to yield impressive performance on Android malware detection. However, most AI-based methods make predictions of suspicious samples in a black-box manner without transparency on models' inference. The expectation on models' explainability and transparency by cyber security and AI practitioners to assure the trustworthiness increases. In this article, we present a novel model-agnostic explanation method for AI models applied for Android malware detection. Our proposed method identifies and quantifies the data features relevance to the predictions by two steps: i) data perturbation that generates the synthetic data by manipulating features' values; and ii) optimization of features attribution values to seek significant changes of prediction scores on the perturbed data with minimal feature values changes. The proposed method is validated by three experiments. We firstly demonstrate that our proposed model explanation method can aid in discovering how AI models are evaded by adversarial samples quantitatively. In the following experiments, we compare the explainability and fidelity of our proposed method with state-of-the-arts, respectively.
翻译:事实证明,AI方法在Android 恶意软件检测方面产生了令人印象深刻的性能。然而,大多数AI方法以黑箱方式对可疑样品作出预测,而模型的推论没有透明度。对模型的解释性和透明度的预期是网络安全以及AI从业人员为确保可信度提高而提出的。在本条中,我们为用于Android 恶意软件检测的AI模型提出了一个新型的模型――不可知性解释方法。我们建议的方法通过两个步骤确定和量化与预测相关的数据特征:一)通过调控特征生成合成数据的数据扰动;二)优化特征归属值,以寻求显著改变被渗透的数据的预测分数,同时进行最低限度的特征改变。拟议的方法得到三个实验的验证。我们首先证明我们提议的模型解释方法有助于发现对抗性样本是如何回避AI模型的。在以下实验中,我们分别将我们拟议方法的可解释性和准确性与最新技术作比较。