Search for: All records

Certain Android applications, such as but not limited to malware, conceal their presence from the user, exhibiting a self-hiding behavior. Consequently, these apps put the user's security and privacy at risk by performing tasks without the user's awareness. Static analysis has been used to analyze apps for self-hiding behavior, but this approach is prone to false positives and suffers from code obfuscation. This research proposes a set of three tools utilizing a dynamic analysis method of detecting self-hiding behavior of an app in the home, installed, and running application lists on an Android emulator. Our approach proves both highly accurate and efficient, providing tools usable by the Android marketplace for enhanced security screening. 

Due to the large computational cost of data classification using deep learning, resource-limited devices, e.g., smart phones, PCs, etc., offload their classification tasks to a cloud server, which offers extensive hardware resources. Unfortunately, since the cloud is an untrusted third-party, users may be reluctant to share their private data with the cloud for data classification. Differential privacy has been proposed as a way of securely classifying data at the cloud using deep learning. In this approach, users conceal their data before uploading it to the cloud using a local obfuscation deep learning model, which is based on a data classification model hosted by the cloud. However, as the obfuscation model assumes that the pre-trained model at the cloud is static, it leads to significant performance degradation under realistic classification models that are constantly being updated. In this paper, we investigate the performance of differentially-private data classification under a dynamic pre-trained model, and a constant obfuscation model. We find that the classification performance decreases as the pre-trained model evolves. We then investigate the classification performance under an obfuscation model that is updated alongside the pre-trained model. We find that with a modest computational effort the obfuscation model can be updated to significantly improve the classification performance. under a dynamic pre-trained model.