The impressive growth of smartphone devices in combination with the rising
ubiquity of using mobile platforms for sensitive applications such as Internet
banking, have triggered a rapid increase in mobile malware. In recent
literature, many studies examine Machine Learning techniques, as the most
promising approach for mobile malware detection, without however quantifying
the uncertainty involved in their detections. In this paper, we address this
problem by proposing a machine learning dynamic analysis approach that provides
provably valid confidence guarantees in each malware detection. Moreover the
particular guarantees hold for both the malicious and benign classes
independently and are unaffected by any bias in the data. The proposed approach
is based on a novel machine learning framework, called Conformal Prediction,
combined with a random forests classifier. We examine its performance on a
large-scale dataset collected by installing 1866 malicious and 4816 benign
applications on a real android device. We make this collection of dynamic
analysis data available to the research community. The obtained experimental
results demonstrate the empirical validity, usefulness and unbiased nature of
the outputs produced by the proposed approach.

通过结合智能手机设备的显著增长以及在敏感应用程序（如互联网银行）中使用移动平台的快速普及，使移动恶意软件迅速增加。本文提出了一种机器学习动态分析方法，为每个恶意软件检测提供可证明有效的置信保证，并且该保证对恶意和良性类别都适用并不受数据偏差的影响。所提出的方法基于一种名为一致性预测的新型机器学习框架，结合了随机森林分类器，在一个真实的 Android 设备上安装了 1866 个恶意应用程序和 4816 个良性应用程序的大规模数据集进行了性能测试。实验结果证明了所提出方法产生的输出的经验有效性、有用性和无偏性。

Android 恶意软件检测与无偏置置信保证

Android Malware Detection with Unbiased Confidence Guarantees

The evolution of mobile malware poses a serious threat to smartphone
security. Today, sophisticated attackers can adapt by maximally sabotaging
machine-learning classifiers via polluting training data, rendering most recent
machine learning-based malware detection tools (such as Drebin, DroidAPIMiner,
and MaMaDroid) ineffective. In this paper, we explore the feasibility of
constructing crafted malware samples; examine how machine-learning classifiers
can be misled under three different threat models; then conclude that injecting
carefully crafted data into training data can significantly reduce detection
accuracy. To tackle the problem, we propose KuafuDet, a two-phase learning
enhancing approach that learns mobile malware by adversarial detection.
KuafuDet includes an offline training phase that selects and extracts features
from the training set, and an online detection phase that utilizes the
classifier trained by the first phase. To further address the adversarial
environment, these two phases are intertwined through a self-adaptive learning
scheme, wherein an automated camouflage detector is introduced to filter the
suspicious false negatives and feed them back into the training phase. We
finally show that KuafuDet can significantly reduce false negatives and boost
the detection accuracy by at least 15%. Experiments on more than 250,000 mobile
applications demonstrate that KuafuDet is scalable and can be highly effective
as a standalone system.

本研究探讨了移动恶意软件的演变对智能手机安全的严重威胁，并提出了一种基于对抗性学习的 KuafuDet 方法来解决机器学习检测在受到恶意样本影响时检测准确率低的问题，该方法不仅可显著减少假阴性率，还可提高至少 15% 的检测准确度。