Abstract: A network-accessible service such as a web site may authenticate users through a login process. In order to detect possibly fraudulent login events, the service may implement a framework based on recorded login events. For example, attributes of multiple recorded login events may be analyzed to create a framework that can be applied to attributes of newly received login requests to predict whether the newly received login requests are fraudulent. The framework may comprise criteria, algorithms, rules, models, and/or techniques, and may be constructed using various means such as pattern recognition, machine learning, and/or cluster analysis.

Abstract: Techniques are described herein for implementing a conference management tool to start, schedule, and manage conferences. The techniques include receiving a scheduling request to schedule a conference from a user device via a communication channel. The communication channel can include a chatbot that is configured to access a calendar and an address book to fulfill the scheduling request. The chatbot may add a calendar association comprising the conference information to the calendar and retrieve contact information associated with one or more participants of the conference from the address book. The chatbot may also send a conference notification to the one or more participants, wherein the conference notification includes conference information that is associated with a conference code that may be presented to the user device.

Abstract: A network-accessible service such as a web site may authenticate users through a login process. In order to detect possibly fraudulent login events, the service may implement a framework based on recorded login events. For example, attributes of multiple recorded login events may be analyzed to create a framework that can be applied to attributes of newly received login requests to predict whether the newly received login requests are fraudulent. The framework may comprise criteria, algorithms, rules, models, and/or techniques, and may be constructed using various means such as pattern recognition, machine learning, and/or cluster analysis.

Abstract: A network-accessible service such as a web site may authenticate users through a login process. In order to detect possibly fraudulent login events, the service may implement a framework based on recorded login events. For example, attributes of multiple recorded login events may be analyzed to create a framework that can be applied to attributes of newly received login requests to predict whether the newly received login requests are fraudulent. The framework may comprise criteria, algorithms, rules, models, and/or techniques, and may be constructed using various means such as pattern recognition, machine learning, and/or cluster analysis.

Abstract: Systems and methods for biometric subscriber account authentication are described. When a subscriber initially accesses subscriber account data maintained by the communication network, a first non-biometric authentication protocol is used. The subscriber may then be invited to set up biometric authentication, which includes generating a private key/public key pair. Subsequently, biometric authentication is performed at the user device to unlock the private key/public key pair, which is then used to support authentication of the subscriber to the communication network using a second authentication protocol.

Abstract: A network-accessible service such as a web site may authenticate users through a login process. In order to detect possibly fraudulent login events, the service may implement a framework based on recorded login events. For example, attributes of multiple recorded login events may be analyzed to create a framework that can be applied to attributes of newly received login requests to predict whether the newly received login requests are fraudulent. The framework may comprise criteria, algorithms, rules, models, and/or techniques, and may be constructed using various means such as pattern recognition, machine learning, and/or cluster analysis.