Abstract
Many traditional machine learning and deep learning algorithms work as a black box and lack interpretability. Attention-based mechanisms can be used to address the interpretability of such models by providing insights into the features that a model uses to make its decisions. Recent success of atten
Highlights
Android is the most popular OS with 71.9% of global market share as of February 2021 [1]
The major contributions of our work are: (a) We built two attention-based classification models with Bi-Long Short Term Memory (LSTM) Attention and Self-Attention, respectively. (b) Using the attention weights from these models, we identified top 200 API-calls for each model, which reflect maliciousness of Android apps
The result might look competitive here, but we note that Machine Learning (ML) requires handpicked features whereas the deep learning models learn the features themselves
Summary
Android is the most popular OS with 71.9% of global market share as of February 2021 [1]. Google Play is one of the largest Android app stores, hosting more than 3 million apps that are collectively used by billions of users. Each LSTM block consists of an input gate, a forget gate and an output gate These gates determine which information from the previous step flows through to the step in time. Their internal cell states can extract and hold temporal information hidden in input sequences. This allows the network to learn when to truncate the gradient and avoid vanishing gradients. LSTMs are only capable of leaning information from the past by parsing the sequence from left-to-right
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
