Abstract: Technologies are described for authenticating a sender identity of an online message. For example, an online message having a purported sender identity can be obtained. Various features can then be extracted from the message, including stylometric features, origin location features, attached file features for any files attached to the message, and embedded URL features. The extracted features can then be compared to a sender profile for a known sender identity matching the purported sender identity, or to one or more sender profiles for recognized suspicious senders if the purported sender identity does not match a known sender identity. The sender profile for a given sender identity can include features extracted from one or more messages previously sent by the sender identity. A global risk score for the message indicating a likelihood that the purported sender identity is inauthentic can be determined based at least in part upon the comparison.

Abstract: A method implements an unsupervised and nonparametric approach for visualizing outliers by invariant detection scoring. The method includes receiving a selection of input data comprising a plurality of input values. The method further includes processing the input data to generate a distance matrix. The method further includes processing the distance matrix to generate neighborhood cumulative distribution function (NCDF) curves. The method further includes processing the NCDF curves to generate scores. The method further includes processing the scores to identify an anomalous value, in the input data, that corresponds to a score, of the scores, meeting a criterion.

Abstract: Technologies are described for authenticating a sender identity of an online message. For example, an online message having a purported sender identity can be obtained. Various features can then be extracted from the message, including stylometric features, origin location features, attached file features for any files attached to the message, and embedded URL features. The extracted features can then be compared to a sender profile for a known sender identity matching the purported sender identity, or to one or more sender profiles for recognized suspicious senders if the purported sender identity does not match a known sender identity. The sender profile for a given sender identity can include features extracted from one or more messages previously sent by the sender identity. A global risk score for the message indicating a likelihood that the purported sender identity is inauthentic can be determined based at least in part upon the comparison.

Abstract: Technologies are described for authenticating a sender identity of an online message. For example, an online message having a purported sender identity can be obtained. Various features can then be extracted from the message, including stylometric features, origin location features, attached file features for any files attached to the message, and embedded URL features. The extracted features can then be compared to a sender profile for a known sender identity matching the purported sender identity, or to one or more sender profiles for recognized suspicious senders if the purported sender identity does not match a known sender identity. The sender profile for a given sender identity can include features extracted from one or more messages previously sent by the sender identity. A global risk score for the message indicating a likelihood that the purported sender identity is inauthentic can be determined based at least in part upon the comparison.

Abstract: Technologies are described for authenticating a sender identity of an online message. For example, an online message having a purported sender identity can be obtained. Various features can then be extracted from the message, including stylometric features, origin location features, attached file features for any files attached to the message, and embedded URL features. The extracted features can then be compared to a sender profile for a known sender identity matching the purported sender identity, or to one or more sender profiles for recognized suspicious senders if the purported sender identity does not match a known sender identity. The sender profile for a given sender identity can include features extracted from one or more messages previously sent by the sender identity. A global risk score for the message indicating a likelihood that the purported sender identity is inauthentic can be determined based at least in part upon the comparison.

Abstract: The present invention provides a system and methods for computer user profiling based on behavioral biometrics. The approach consists of establishing distinctive profiles for computer users based on how they use a motion-based input device such as, but not limited to, a mouse and/or a keyboard. The profiles computed in the present invention are more accurate than those obtained through the traditional statistical profiling techniques, since they are based on distinctive biological characteristics of users.

Abstract: A password generator for use with a detector and a verifier in an encapsulated system is provided, as is a system for generating and verifying passwords. The password generator comprises a support, a sensor for detecting a signal from the detector, a data transmitter for transmitting binary data as pulses, a processor that is initialized by the verifier and that controls the data to be sent, a controller for activating the processor and a connector to releasably connect the password generator with the verifier. The system employs a mouse as the detector.

Abstract: A password generator for use with a detector and a verifier in an encapsulated system is provided, as is a system for generating and verifying passwords. The password generator comprises a support, a sensor for detecting a signal from the detector, a data transmitter for transmitting binary data as pulses, a processor that is initialized by the verifier and that controls the data to be sent, a controller for activating the processor and a connector to releasably connect the password generator with the verifier. The system employs a mouse as the detector.

Abstract: A biometric intrusion detection system based on mouse dynamics analysis, the analysis of mouse dynamics for a specific user generates a number of factors (Mouse Dynamics Signature) which can be used to ensure the identity of the user, an intelligent detection technique is developed to recognize differences in behaviors and detect intrusion.