Abstract: Behavioral analysis of a mobile application is performed to determine whether the application is malicious. During analysis, various user interactions are simulated in an emulated environment to activate many possible resulting behaviors of an application. The behaviors are classified as hard or soft signals. A probability of the application being malicious is determined through combining soft signals, and the application is classified as malicious or non-malicious. Users of the application, the developer of the application, or a distributor of the application are notified of the application classification to enable responsive action.

Abstract: Behavioral analysis of a mobile application is performed to determine whether the application is malicious. During analysis, various user interactions are simulated in an emulated environment to activate many possible resulting behaviors of an application. The behaviors are classified as hard or soft signals. A probability of the application being malicious is determined through combining soft signals, and the application is classified as malicious or non-malicious. Users of the application, the developer of the application, or a distributor of the application are notified of the application classification to enable responsive action.

Abstract: Behavioral analysis of a mobile application is performed to determine whether the application is malicious. During analysis, various user interactions are simulated in an emulated environment to activate many possible resulting behaviors of an application. The behaviors are classified as hard or soft signals. A probability of the application being malicious is determined through combining soft signals, and the application is classified as malicious or non-malicious. Users of the application, the developer of the application, or a distributor of the application are notified of the application classification to enable responsive action.

Abstract: Behavioral analysis of a mobile webpage is performed to determine whether the webpage is malicious. During analysis, the webpage is visited by an emulated mobile device to cause behaviors to occur which may be malicious. The behaviors occurring after accessing the webpage are stored. The behaviors are classified as hard or soft signals. A probability of the webpage being malicious is determined through combining soft signals, and the webpage is classified as malicious or non-malicious. Users of the webpage, the developer of the webpage, or a distributor of the webpage are notified of the webpage classification to enable responsive action.

Abstract: Diversity information associated with a set of advertisement tags is determined. Example ways of determining diversity include determining a list of distinct Uniform Resource Locators, determining a list of distinct domains, and determining whether an advertisement includes one or more dynamic elements. Scans are adaptively performed based on the determined diversity information. Scanning is performed more frequently for advertisement tags having higher associated diversities and scanning is performed less frequently for advertisement tags having lower associated diversities.

Abstract: Behavioral analysis of a mobile application is performed to determine whether the application is malicious. During analysis, various user interactions are simulated in an emulated environment to activate many possible resulting behaviors of an application. The behaviors are classified as hard or soft signals. A probability of the application being malicious is determined through combining soft signals, and the application is classified as malicious or non-malicious. Users of the application, the developer of the application, or a distributor of the application are notified of the application classification to enable responsive action.

Abstract: Behavioral analysis of a mobile webpage is performed to determine whether the webpage is malicious. During analysis, the webpage is visited by an emulated mobile device to cause behaviors to occur which may be malicious. The behaviors occurring after accessing the webpage are stored. The behaviors are classified as hard or soft signals. A probability of the webpage being malicious is determined through combining soft signals, and the webpage is classified as malicious or non-malicious. Users of the webpage, the developer of the webpage, or a distributor of the webpage are notified of the webpage classification to enable responsive action.

Abstract: Diversity information associated with a set of advertisement tags is determined. Example ways of determining diversity include determining a list of distinct Uniform Resource Locators, determining a list of distinct domains, and determining whether an advertisement includes one or more dynamic elements. Scans are adaptively performed based on the determined diversity information. Scanning is performed more frequently for advertisement tags having higher associated diversities and scanning is performed less frequently for advertisement tags having lower associated diversities.