Unleash the Magic for Android: Adversarial Detection of Mobile Malware


Contact: ecnuchensen@gmail.com    minhuixue@nyu.edu



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 and DroidAPIMiner) ineffective.

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.

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 KuafuDet significantly reduces false negatives and boosts the detection accuracy by at least 15%.


Sen Chen, Minhui Xue, Lingling Fan, Shuang Hao, Lihua Xu, and Haojin Zhu, “When Big Data Meets Cybersecurity: Adversarial Detection of Mobile Applications”, Elsevier Computers & Security, 2017. (Under Submission)


We are happy to release our results to the community. Please visit the download page for detailed instructions.


We would like to thank Pwnzen Infotech Inc. for providing us with a copy of mobile malware to conduct the study, especially the Pwnzen Infotech Inc. co-founder Zhushou Tang for exchanging helpful industry experience. We would also like to thank the anonymous referees for their valuable comments.