Pindrop Security, Inc.

Hassan Kingravi

David Bryan Dewey

Scott Strong

John Cornwell

Nick Gaubitch

Aditya Kurve

Aude Marzuoli

Systems, methods, and computer-readable media for call classification and for training a model for call classification, an example method comprising: receiving DTMF information from a plurality of calls; determining, for each of the calls, a feature vector including statistics based on DTMF information such as DTMF residual signal comprising channel noise and additive noise; training a model for classification; comparing a new call feature vector to the model; predicting a device type and geographic location based on the comparison of the new call feature vector to the model; classifying the call as spoofed or genuine; and authenticating a call or altering an IVR call flow.

Call classification through analysis of DTMF events

Systems and methods for classification using an explicit feature map or an approximate feature map based on a relative locality measure. In at least one embodiment, a method of authenticating a user operates data points having feature vectors pertaining to user events comprises selecting an approximate feature map based on a subset of features in each data point and a relative locality measure of a cluster including a plurality of the data points; mapping, to a feature space, the subset of features in each data point and a new data point pertaining to a phone call of the user using the selected approximate feature map; determining a classification of the new data point based on its relative locality measure with respect to a cluster in the feature space; storing the classification of the new data point in a memory device; and authenticating the user during the phone call.

Feature embeddings with relative locality for fast profiling of users on streaming data

Methods and systems for detecting new calls from an existing spam or robocaller and aggregating calls that originate from the same infrastructure using a telephony honeypot are disclosed. An example method may receive a telephone call to a telephony honeypot and store metadata and a call audio recording associated with the telephone call. A transcript may be created of the call audio recording. Audio features may be extracted from the call audio recording. The transcript may be compared to other previously-received transcripts in order to determine a similarity between the call and previously-received calls. Audio features and metadata may also be compared to determine whether the call is similar to other previously-received calls. If a call is similar, the call may be identified with the same spam campaign or robocaller as the similar, previously-received call.

Growing community of inventors

Atlanta, GA, United States of America

Hassan Kingravi