Abstract: Active learning-based fraud detection techniques are provided in adaptive authentication systems. An authentication request from an authentication requestor is processed by receiving the authentication request from the authentication requester; comparing current data for the user associated with the user identifier with historical data for the user; generating an adaptive authentication result based on the comparison indicating a likelihood current user data is associated with a fraudulent user; and performing one or more additional authentication operations to improve learning if the request satisfies one or more predefined non-risk based criteria. The predefined non-risk based criteria comprises, for example, (i) the request receiving a riskiness score below a threshold based on current data and wherein the request was expected to have a risk score above a threshold, or (ii) the request being in a bucket having a number of tagged events below a threshold.

Abstract: Similarity-based fraud detection techniques are provided in adaptive authentication systems. A method is provided for determining if an event is fraudulent by obtaining a plurality of tagged events and one or more untagged events, wherein the tagged events indicate a likelihood of whether the corresponding event was fraudulent; constructing a graph, wherein each node in the graph represents an event and has a value representing a likelihood of whether the corresponding event was fraudulent and wherein similar transactions are connected via weighted links; diffusing through weights in the graph to assign values to nodes such that neighbors of nodes having non-zero values receive similar values as the neighbors; and classifying whether at least one of the one or more untagged events is fraudulent based on the assigned values.

Abstract: An improved technique involves automatically producing a set of KBA questions using values of attributes associated with correctly answered questions. A KBA question server obtains such attribute values from a prior set of pilot questions taken from users who were successfully authenticated. Examples of attributes include a source of facts in a question, placement of facts in a question, and question structure. The KBA question server then generates optimal formatting rules based on the attribute values; such formatting rules define a relationship between facts used to derive KBA questions and the words used to express the KBA questions to users. The KBA question generator then produces KBA questions according to the formatting rules.

Abstract: There is disclosed a technique for use in assessing the risk of information leakage. The technique receives a set of facts that have references to individuals associated with an organization. Based on the received facts, a link is detected between an individual associated with the organization and an occurrence indicative of risk. A connection is identified between the individual and confidential information within the organization. Based on the detected link and the identified connection, the risk is determined of the confidential information being leaked in an unauthorized manner by the individual.

Abstract: There is disclosed some techniques for processing an authentication request which includes a user identifier and current user data. In one example, the technique comprises receiving the authentication request at an adaptive authentication system which includes a database having a set of entries with each entry of the set of entries including an identifier and previous user data in connection with previous authentication requests. The adaptive authentication system being constructed and arranged to perform an adaptive authentication operation on the authentication request as well as an unsupervised machine learning operation on the authentication request.

Abstract: An improved technique tailors a biometric challenge activity to a particular user. The particular user submits electronic input from which an authentication system extracts information concerning traits of the particular user; such traits can include keystroke and swiping patterns, handheld device positions, and place of origin. An authentication server maps values of user attributes such as place of origin, age, and UI device to the extracted traits. The authentication server then selects biometric challenges for the particular user based on user attributes having values which deviate most from a mean value of that attribute taken across a population of users. That is, the authentication server bases biometric challenges on the most distinguishing traits of the particular user.

Abstract: An improved authentication technique employs a user's mobile device to obtain a picture of the user from which facial geometry is extracted and applied as part of an authentication operation of the user to the remote network. In some examples, a server stores facial geometry for different users along with associated PINs. By matching facial geometry of the user with facial geometry on the server, the user's PIN can be obtained, without the user ever having to register or remember the PIN.

Abstract: A method of operating a VM server (VMS) is described, including (a) executing a VM instance (VMI) at the VMS, the VMI having a remote display within a terminal program of a client computer, the terminal program being configured to send commands received by the client from a user to the VMS to affect operation of the VMI, (b) running a browser within the VMI, the browser having a connection to a secure web application running on a web application server, the commands sent from the terminal program to the VMS allowing the user to interact with the web application via the terminal program and the browser running on the VMI, (c) at the VMS, asynchronously collecting information in connection with the commands sent from the user to the VMS, and (d) at the VMS, asynchronously sending the collected information to an analysis server to be analyzed for anomalous behavior.

Abstract: An improved technique of processing an authentication request from an authentication requestor involves an adaptive authentication device comparing a behavioral history of fact values associated with a user over a current time window with a user's baseline profile that includes a behavioral history of the fact values. The adaptive authentication device accesses such a behavioral history over several previous time windows from a database whose entries include a user identifier, a time interval and user data which represents fact value behavioral history over the time interval. When the device receives an authentication request from an authentication requestor, the adaptive authentication device matches a username of the request with a user identifier of an entry of the database whose time period is the current time period. The adaptive authentication device then updates fact values representing the user's current behavioral history and compares the current behavioral history to the user's baseline profile.

Abstract: An improved technique identifies risky transactions from a set of transactions and updates risk scores only for those transactions identified as risky. Along these lines, a transaction sorting engine sorts the set of transactions according to risk score. The transaction sorting engine identifies as risky those transactions having risk scores above a specified percentile; for instance, the transactions having risk scores above the 90th percentile would be identified as risky. Some time later, a risk score engine adjusts, based on new historical transaction data, Bayesian weights which it uses to compute risk scores. The transaction sorting engine sends to the risk score engine only those transactions it identified as risky. The risk score engine computes new risk scores for the risky transactions and makes the new risk scores available to the transaction sorting engine so that it can sort all of current transactions (e.g., received within the past week).