At&t Intellectual Property I, L.p.

University of Minnesota

Yu Jin

Ann Eileen Skudlark

Lien K Tran

Jeffrey Erman

Subhabrata Bapi Sen

Patrick Guy Haffner

Nicholas G Duffield

Nan Jiang

Zhi-Li Zhang

Wen-Ling Hsu

Cynthia Cama

Abhinav Srivastava

A cloud based mobile internet protocol messaging spam defense. Short message service (SMS) messages are analyzed by a cloud based virtual machine to determine if should be considered potentially unwanted messages (e.g., spam). The cloud based virtual machine uses a user specific algorithm for determining if a message should be considered to be a potentially unwanted message. Messages that are determined to be potentially unwanted messages trigger a notification to be sent to a user device associated with the virtual machine. The notification requests confirmation from the user that the potentially unwanted message is an unwanted message. The user's response to a request for confirmation is then used to update an unwanted message database associated with the user and the user device.

Cloud-based spam detection

System and method for cloud based IP mobile messaging spam detection and defense

Network traffic usage information for a set of registered devices is monitored, analyzed, and reported within a cellular service provider portion of a communications network. The network traffic usage information can relate to data traffic, voice traffic, and/or short message service traffic. Reporting the network traffic usage information is customizable such that parameters associated with the network traffic usage can be changed, depending on the parameters that are of current interest to an organization affiliated with the set of registered devices.

Management of group mobile device network traffic usage

A crowd-sourced mobile messaging spam detection and defense system includes an application running on a mobile device. The application uses an unwanted message detection algorithm to analyze and classify messages as potential unwanted messages. The potential unwanted messages are presented to a user for confirmation that the messages are unwanted messages. In response to confirmation, the mobile device transmits a notification to a virtual machine associated with the user. The virtual machine uses the notification to update the unwanted message detection algorithm which may then be transmitted to the mobile device. The virtual machine may also transmit the notification to a global virtual machine. The global virtual machine may use the notification to update a set of classification rules maintained by the global virtual machine and transmit the set of classification rules as necessary to the multiple virtual machines for use in updating the unwanted message detection algorithm.

System and method for crowd-sourcing mobile messaging spam detection and defense

A method and system for identifying short message service (SMS) spammers identifies senders as spammers by determining that the senders are sending SMS messages to devices included in a grey phone space. Devices in the grey phone space are identified using various methods including an analysis of call detail records. A grey ratio for a sender is determined as a ratio of messages sent to grey phone numbers by the sender to messages sent to all phone numbers by the sender. A sender is identified based on a difference between the grey ratio for the sender and a second grey ratio being above a threshold.

System and method for fast accurate detection of SMS spam numbers via monitoring grey phone space

System and method for fast and accurate detection of SMS spam numbers via monitoring grey phone space

A traffic classifier has a plurality of binary classifiers, each associated with one of a plurality of calibrators. Each calibrator trained to translate an output score of the associated binary classifier into an estimated class probability value using a fitted logistic curve, each estimated class probability value indicating a probability that the packet flow on which the output score is based belongs to the traffic class associated with the binary classifier associated with the calibrator. The classifier training system configured to generate a training data based on network information gained using flow and packet sampling methods. In some embodiments, the classifier training system configured to generate reduced training data sets, one for each traffic class, reducing the training data related to traffic not associated with the traffic class.

Scalable traffic classifier and classifier training system

In one embodiment, the present disclosure is a method and apparatus for classifying applications using the collective properties of network traffic. In one embodiment, a method for classifying traffic in a communication network includes receiving a traffic activity graph, the traffic activity graph comprising a plurality of nodes interconnected by a plurality of edges, where each of the nodes represents an endpoint associated with the communication network and each of the edges represents traffic between a corresponding pair of the nodes, generating an initial set of inferences as to an application class associated with each of the edges, based on at least one measured statistic related to at least one traffic flow in the communication network, and refining the initial set of inferences based on a spatial distribution of the traffic flows, to produce a final traffic activity graph.

Growing community of inventors

Madison, NJ, United States of America

Yu Jin