Abstract: Described is a technology by which phishing-related data sources are processed into aggregated data and a given site evaluated the aggregated data using a predictive model to automatically determine whether the given site is likely to be a phishing site. The predictive model may be built using machine learning based on training data, e.g., including known phishing sites and/or known non-phishing sites. To determine whether an object corresponding to a site is likely a phishing-related object are described, various criteria are evaluated, including one or more features of the object when evaluated. The determination is output in some way, e.g., made available to a reputation service, used to block access to a site or warn a user before allowing access, and/or used to assist a hand grader in being more efficient in evaluating sites.

Abstract: A system and method for detecting an electronic communication such as an email, an instant messaging session, or a chat session that relates to an unsafe behavior directed to or engaged by a user. Instructions are adapted to analyze one or more features of the electronic communication, which is sent or received by the user. Instructions are adapted to categorize the electronic communication as relating to the unsafe behavior based on the analyzed features. A report is generated if the electronic communication is categorized as relating to the unsafe behavior. Instructions are adapted to send the report to a responsible person such as a parent, guardian, or other responsible person of the user. The report informs the responsible person that the electronic communication possibly relates to the unsafe behavior.

Abstract: A self-improving system and method for classifying a plurality of digital documents such as web pages into one or more categories. Textual features and contextual features are extracted from a digital document and submitted to a committee machine. The committee machine assigns a rating to the digital document as a function of the extracted features and provides the location such as a URL for the digital document and its rating to an output data store. The output data store stores a list of locations for the plurality of digital documents. The output data store further segregates the locations of the digital document into categories based on the content of each document as indicated by the assigned rating.