一句话：提出引导式再训练方法，利用基检测器的正确与错误预测，通过监督对比学习重新嵌入困难样本并训练辅助分类器，显著降低 Android 恶意软件检测错误率。
Android 恶意软件检测器（尤其是基于机器学习的方法）在面对与合法应用高度相似的“困难”样本时错误率较高。本文提出引导式再训练（Guided Retraining），一种基于监督表示学习的方法，旨在提升恶意软件检测器性能。首先根据检测器输出的预测概率将数据集划分为“容易”和“困难”两个子集：对容易子集直接使用基检测器进行预测，因为其错误率天然较低；对困难子集则应用引导式再训练，利用基检测器的正确预测和错误作为监督信号，通过监督对比学习学习新的样本嵌入，并训练一个辅助分类器进行最终分类。作者在超过 26.5 万个恶意与良性应用上，对四种先进的 Android 恶意软件检测方法进行了验证。实验结果表明，引导式再训练能够消除困难样本上最多 45.19% 的预测错误。该方法具有通用性，可推广至其他二分类任务。
The popularity of Android OS has made it an appealing target for malware developers. To evade detection, including by ML-based techniques, attackers invest in creating malware that closely resemble legitimate apps, challenging the state of the art with difficult-to-detect samples. In this paper, we propose Guided Retraining, a supervised representation learning-based method for boosting the performance of malware detectors. To that end, we first split the experimental dataset into subsets of “easy” and “difficult” samples, where difficulty is associated to the prediction probabilities yielded by a malware detector. For the subset of “easy” samples, the base malware detector is used to make the final predictions since the error rate on that subset is low by construction. Our work targets the second subset containing “difficult” samples, for which the probabilities are such that the classifier is not confident on the predictions, which have high error rates. We apply our Guided Retraining method on these difficult samples to improve their classification. Guided Retraining leverages the correct predictions and the errors made by the base malware detector to guide the retraining process. Guided Retraining learns new embeddings of the difficult samples using Supervised Contrastive Learning and trains an auxiliary classifier for the final predictions. We validate our method on four state-of-the-art Android malware detection approaches using over 265k malware and benign apps. Experimental results show that Guided Retraining can boost state-of-the-art detectors by eliminating up to 45.19% of the prediction errors that they make on difficult samples. We note furthermore that our method is generic and designed to enhance the performance of binary classifiers for other tasks beyond Android malware detection.
@inproceedings{DaoudiABK23,
title = {Guided Retraining to Enhance the Detection of Difficult Android Malware},
author = {Nadia Daoudi and Kevin Allix and Tegawendé F. Bissyandé and Jacques Klein},
booktitle = {ISSTA},
year = {2023},
doi = {10.1145/3597926.3598123}
}