Android is a widely distributed mobile operating system developed especially for mobile devices with touch screens. It is an open source, Google-distributed Linux-based mobile operating system. Since Android is open source, it enables Android devices to be targeted effectively by malware developers. Third-party markets do not search for malicious applications in their databases, so installing Android Application Packages (APKs) from these uncontrolled market places is often risky. Without user’s notice, these malware infected applications gain access to private user data, send text messages that costs the user, or hide malware apk file inside another application. The total number of new samples of Android malware amounted to 482,579 per month as of March 2020. In this paper deep learning approach that focuses on malware detection in android apps to protect data on user devices. We use different static features that are present in an Android application for the implementation of the proposed system. The system extracts various static features and gives them to the classifier for deep learning and shows the results. This proposed system will assist users in checking applications that are not downloaded from the official market.
Recently machine learning algorithms are utilized for identifying network threats. Threats otherwise called as intrusions, will harm the network in a stern manner, thus it must be dealt cautiously. In the proposed research work, a deep learning model has been applied to recognize and categorize unanticipated and unpredictable cyber-attacks. The UNSW NB-15 dataset has a vital number of features which will be learned by the hidden layers present in the suggested model and classified by the output layer. The suitable quantity of layers, neurons in each layer and the optimizer utilized in the proposed work are obtained through a sequence of trial and error experiments. The concluding model acquired can be utilized for estimating future malicious attacks. There are several data preprocessing techniques available at our disposal. We used two types of techniques in our experiment: 1) Log transformation, MinMaxScaling and factorize technique; and 2) Z-score encoding and dummy encoding technique. In general, the selection of data preprocessing techniques has a direct impact on the output performed by any machine learning process and our research, attempts to prove this concept.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.