公开(公告)号：US20220121868A1

公开(公告)日：2022-04-21

申请号：US17503152

申请日：2021-10-15

Applicant: Pindrop Security, Inc.

Inventor： Tianxiang CHEN ,  Elie KHOURY

IPC: G06K9/00 ,  G06K9/62 ,  G10L17/22

Abstract: The embodiments execute machine-learning architectures for biometric-based identity recognition (e.g., speaker recognition, facial recognition) and deepfake detection (e.g., speaker deepfake detection, facial deepfake detection). The machine-learning architecture includes layers defining multiple scoring components, including sub-architectures for speaker deepfake detection, speaker recognition, facial deepfake detection, facial recognition, and lip-sync estimation engine. The machine-learning architecture extracts and analyzes various types of low-level features from both audio data and visual data, combines the various scores, and uses the scores to determine the likelihood that the audiovisual data contains deepfake content and the likelihood that a claimed identity of a person in the video matches to the identity of an expected or enrolled person. This enables the machine-learning architecture to perform identity recognition and verification, and deepfake detection, in an integrated fashion, for both audio data and visual data.

公开(公告)号：US20220006899A1

公开(公告)日：2022-01-06

申请号：US17365970

申请日：2021-07-01

Applicant: PINDROP SECURITY, INC.

Inventor： Kedar PHATAK ,  Jayaram RAGHURAM

IPC: H04M3/22 ,  H04L29/06 ,  G06N20/00

Abstract: Embodiments described herein provide for a fraud detection engine for detecting various types of fraud at a call center and a fraud importance engine for tailoring the fraud detection operations to relative importance of fraud events. Fraud importance engine determines which fraud events are comparative more important than others. The fraud detection engine comprises machine-learning models that consume contact data and fraud importance information for various anti-fraud processes. The fraud importance engine calculates importance scores for fraud events based on user-customized attributes, such as fraud-type or fraud activity. The fraud importance scores are used in various processes, such as model training, model selection, and selecting weights or hyper-parameters for the ML models, among others. The fraud detection engine uses the importance scores to prioritize fraud alerts for review. The fraud importance engine receives detection feedback, which contacts involved false negatives, where fraud events were undetected but should have been detected.

公开(公告)号：US20210326421A1

公开(公告)日：2021-10-21

申请号：US17231672

申请日：2021-04-15

Applicant: PINDROP SECURITY, INC.

Inventor： Elie KHOURY ,  Ganesh SIVARAMAN ,  Avrosh KUMAR ,  Ivan ANTOLIC-SOBAN

IPC: G06F21/32 ,  G10L17/18 ,  G10L17/04 ,  G10L17/24 ,  G06N20/00

Abstract: Embodiments described herein provide for a voice biometrics system execute machine-learning architectures capable of passive, active, continuous, or static operations, or a combination thereof. Systems passively and/or continuously, in some cases in addition to actively and/or statically, enrolling speakers as the speakers speak into or around an edge device (e.g., car, television, radio, phone). The system identifies users on the fly without requiring a new speaker to mirror prompted utterances for reconfiguring operations. The system manages speaker profiles as speakers provide utterances to the system. Machine-learning architectures implement a passive and continuous voice biometrics system, possibly without knowledge of speaker identities. The system creates identities in an unsupervised manner, sometimes passively enrolling and recognizing known or unknown speakers. The system offers personalization and security across a wide range of applications, including media content for over-the-top services and IoT devices (e.g., personal assistants, vehicles), and call centers.

公开(公告)号：US20210233541A1

公开(公告)日：2021-07-29

申请号：US17155851

申请日：2021-01-22

Applicant: PINDROP SECURITY, INC.

Inventor： Tianxiang CHEN ,  Elie KHOURY

IPC: G10L17/18 ,  G10L17/04 ,  G10L17/22 ,  G10L17/02

Abstract: Embodiments described herein provide for systems and methods for implementing a neural network architecture for spoof detection in audio signals. The neural network architecture contains a layers defining embedding extractors that extract embeddings from input audio signals. Spoofprint embeddings are generated for particular system enrollees to detect attempts to spoof the enrollee's voice. Optionally, voiceprint embeddings are generated for the system enrollees to recognize the enrollee's voice. The voiceprints are extracted using features related to the enrollee's voice. The spoofprints are extracted using features related to features of how the enrollee speaks and other artifacts. The spoofprints facilitate detection of efforts to fool voice biometrics using synthesized speech (e.g., deepfakes) that spoof and emulate the enrollee's voice.

公开(公告)号：US20210150010A1

公开(公告)日：2021-05-20

申请号：US17157837

申请日：2021-01-25

Applicant: PINDROP SECURITY, INC.

Inventor： Scott Strong ,  Kailash Patil ,  David Dewey ,  Raj Bandyopadhyay ,  Telvis Calhoun ,  Vijay Balasubramaniyan

IPC: G06F21/32 ,  G06N20/00 ,  G06F21/55 ,  H04M3/493 ,  H04W12/128 ,  H04M3/527 ,  H04M15/00 ,  H04W12/12

Abstract: Systems and methods for call detail record (CDR) analysis to determine a risk score for a call and identify fraudulent activity and for fraud detection in Interactive Voice Response (IVR) systems. An example method may store information extracted from received calls. Queries of the stored information may be performed to select data using keys, wherein each key relates to one of the received calls, and wherein the queries are parallelized. The selected data may be transformed into feature vectors, wherein each feature vector relates to one of the received calls and includes a velocity feature and at least one of a behavior feature or a reputation feature. A risk score for the call may be generated during the call based on the feature vectors.

公开(公告)号：US10902105B2

公开(公告)日：2021-01-26

申请号：US16515823

申请日：2019-07-18

Applicant: PINDROP SECURITY, INC.

Inventor： Scott Strong ,  Kailash Patil ,  David Dewey ,  Raj Bandyopadhyay ,  Telvis Calhoun ,  Vijay Balasubramaniyan

IPC: H04M3/527 ,  G06F21/32 ,  G06N20/00 ,  G06F21/55 ,  H04M3/493 ,  H04W12/12 ,  H04M15/00 ,  H04M7/00

Abstract: Systems and methods for call detail record (CDR) analysis to determine a risk score for a call and identify fraudulent activity and for fraud detection in Interactive Voice Response (IVR) systems. An example method may store information extracted from received calls. Queries of the stored information may be performed to select data using keys, wherein each key relates to one of the received calls, and wherein the queries are parallelized. The selected data may be transformed into feature vectors, wherein each feature vector relates to one of the received calls and includes a velocity feature and at least one of a behavior feature or a reputation feature. A risk score for the call may be generated during the call based on the feature vectors.

公开(公告)号：US20200321009A1

公开(公告)日：2020-10-08

申请号：US16907951

申请日：2020-06-22

Applicant: PINDROP SECURITY, INC.

Inventor： Elie KHOURY ,  Parav NAGARSHETH ,  Kailash PATIL ,  Matthew GARLAND

IPC: G10L17/02 ,  G10L17/04 ,  G10L25/24 ,  G10L17/18 ,  G10L19/02 ,  G10L17/06 ,  G10L17/00

Abstract: An automated speaker verification (ASV) system incorporates a first deep neural network to extract deep acoustic features, such as deep CQCC features, from a received voice sample. The deep acoustic features are processed by a second deep neural network that classifies the deep acoustic features according to a determined likelihood of including a spoofing condition. A binary classifier then classifies the voice sample as being genuine or spoofed.

公开(公告)号：US10553218B2

公开(公告)日：2020-02-04

申请号：US15709232

申请日：2017-09-19

Applicant: PINDROP SECURITY, INC.

Inventor： Elie Khoury ,  Matthew Garland

IPC: G10L17/00 ,  G10L17/18 ,  G10L17/02 ,  G10L17/06

Abstract: In a speaker recognition apparatus, audio features are extracted from a received recognition speech signal, and first order Gaussian mixture model (GMM) statistics are generated therefrom based on a universal background model that includes a plurality of speaker models. The first order GMM statistics are normalized with regard to a duration of the received speech signal. The deep neural network reduces a dimensionality of the normalized first order GMM statistics, and outputs a voiceprint corresponding to the recognition speech signal.

公开(公告)号：US10542135B2

公开(公告)日：2020-01-21

申请号：US16200379

申请日：2018-11-26

Applicant: PINDROP SECURITY, INC.

Inventor： Lance Douglas

IPC: H04M15/00 ,  H04M17/00 ,  H04M3/22 ,  H04M3/436 ,  H04M7/00 ,  H04L29/06

Abstract: Aspects of the invention determining a threat score of a call traversing a telecommunications network by leveraging the signaling used to originate, propagate and terminate the call. Outer-edge data utilized to originate the call may be analyzed against historical, or third party real-time data to determine the propensity of calls originating from those facilities to be categorized as a threat. Storing the outer edge data before the call is sent over the communications network permits such data to be preserved and not subjected to manipulations during traversal of the communications network. This allows identification of threat attempts based on the outer edge data from origination facilities, thereby allowing isolation of a compromised network facility that may or may not be known to be compromised by its respective network owner. Other aspects utilize inner edge data from an intermediate node of the communications network which may be analyzed against other inner edge data from other intermediate nodes and/or outer edge data.

公开(公告)号：US10440178B2

公开(公告)日：2019-10-08

申请号：US16289957

申请日：2019-03-01

Applicant: PINDROP SECURITY, INC.

Inventor： Payas Gupta ,  Terry Nelms, II

IPC: H04W12/06 ,  H04M3/436 ,  H04W4/16 ,  H04M3/42

Abstract: In an illustrative embodiment, a user device may block all the phone numbers used by an enterprise. When an enterprise wants to call the user, the enterprise may notify the user device through a separate secure channel that an enterprise phone number is in the process of making a phone call to the user device. The secure channel may include an authentication server that may request the user device to unblock the enterprise phone number. An incoming phone call from the enterprise phone number therefore can be trusted. After the phone call is terminated, the user device may again block the enterprise phone number. An attacker may not have access to the authentication server and a phone call from the attacker with a spoofed enterprise phone number (now blocked) may be dropped by the user device.