A common problem in machine learning-based malware detection is that training data may contain noisy labels and it is challenging to make the training data noise-free at a large scale. To address this problem, we propose a generic framework to reduce the noise level of training data for the training of any machine learning-based Android malware detection. Our framework makes use of all intermediate states of two identical deep learning classification models during their training with a given noisy training dataset and generate a noise-detection feature vector for each input sample. Our framework then applies a set of outlier detection algorithms on all noise-detection feature vectors to reduce the noise level of the given training data before feeding it to any machine learning based Android malware detection approach. In our experiments with three different Android malware detection approaches, our framework can detect significant portions of wrong labels in different training datasets at different noise ratios, and improve the performance of Android malware detection approaches.

View More Papers

icLibFuzzer: Isolated-context libFuzzer for Improving Fuzzer Comparability

Yu-Chuan Liang, Hsu-Chun Hsiao (National Taiwan University)

Read More

Digital Technologies in Pandemic: The Good, the Bad and...

Moderator: Ahmad-Reza Sadeghi, TU Darmstadt, Germany Panelists: Mario Guglielmetti, Legal Officer, European Data Protection Supervisor* Jaap-Henk Hoepman, Radbaud University, The...

Read More

An Analysis of First-Party Cookie Exfiltration due to CNAME...

Tongwei Ren (Worcester Polytechnic Institute), Alexander Wittmany (University of Kansas), Lorenzo De Carli (Worcester Polytechnic Institute), Drew Davidsony (University of...

Read More

POSEIDON: Privacy-Preserving Federated Neural Network Learning

Sinem Sav (EPFL), Apostolos Pyrgelis (EPFL), Juan Ramón Troncoso-Pastoriza (EPFL), David Froelicher (EPFL), Jean-Philippe Bossuat (EPFL), Joao Sa Sousa (EPFL),...

Read More