Patents by Inventor Vijay Balasubramaniyan
Vijay Balasubramaniyan has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11849065Abstract: Various embodiments of the invention are detection systems and methods for detecting call provenance based on call audio. An exemplary embodiment of the detection system can comprise a characterization unit, a labeling unit, and an identification unit. The characterization unit can extract various characteristics of networks through which a call traversed, based on call audio. The labeling unit can be trained on prior call data and can identify one or more codecs used to encode the call, based on the call audio. The identification unit can utilize the characteristics of traversed networks and the identified codecs, and based on this information, the identification unit can provide a provenance fingerprint for the call. Based on the call provenance fingerprint, the detection system can identify, verify, or provide forensic information about a call audio source.Type: GrantFiled: June 3, 2021Date of Patent: December 19, 2023Assignee: Georgia Tech Research CorporationInventors: Vijay Balasubramaniyan, Mustaque Ahamad, Patrick Gerard Traynor, Michael Thomas Hunter, Aamir Poonawalla
-
Patent number: 11748463Abstract: 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.Type: GrantFiled: January 25, 2021Date of Patent: September 5, 2023Assignee: PINDROP SECURITY, INC.Inventors: Scott Strong, Kailash Patil, David Dewey, Raj Bandyopadhyay, Telvis Calhoun, Vijay Balasubramaniyan
-
Publication number: 20220392452Abstract: Disclosed are systems and methods including computing-processes executing machine-learning architectures extract vectors representing disparate types of data and output predicted identities of users accessing computing services, without express identity assertions, and across multiple computing services, analyzing data from multiple modalities, for various user devices, and agnostic to architectures hosting the disparate computing service. The system invokes the identification operations of the machine-learning architecture, which extracts biometric embeddings from biometric data and context embeddings representing all or most of the types of metadata features analyzed by the system. The context embeddings help identify a subset of potentially matching identities of possible users, which limits the number of biometric-prints the system compares against an inbound biometric embedding for authentication.Type: ApplicationFiled: June 3, 2022Publication date: December 8, 2022Applicant: Pindrop Security, Inc.Inventors: Payas GUPTA, Elie KHOURY, Terry NELMS, II, Vijay BALASUBRAMANIYAN
-
Publication number: 20220392453Abstract: Disclosed are systems and methods including computing-processes executing machine-learning architectures extract vectors representing disparate types of data and output predicted identities of users accessing computing services, without express identity assertions, and across multiple computing services, analyzing data from multiple modalities, for various user devices, and agnostic to architectures hosting the disparate computing service. The system invokes the identification operations of the machine-learning architecture, which extracts biometric embeddings from biometric data and context embeddings representing all or most of the types of metadata features analyzed by the system. The context embeddings help identify a subset of potentially matching identities of possible users, which limits the number of biometric-prints the system compares against an inbound biometric embedding for authentication.Type: ApplicationFiled: June 3, 2022Publication date: December 8, 2022Applicant: Pindrop Security, Inc.Inventors: Payas Gupta, Elie KHOURY, Terry Nelms, II, Vijay BALASUBRAMANIYAN
-
Publication number: 20210295861Abstract: Various embodiments of the invention are detection systems and methods for detecting call provenance based on call audio. An exemplary embodiment of the detection system can comprise a characterization unit, a labeling unit, and an identification unit. The characterization unit can extract various characteristics of networks through which a call traversed, based on call audio. The labeling unit can be trained on prior call data and can identify one or more codecs used to encode the call, based on the call audio. The identification unit can utilize the characteristics of traversed networks and the identified codecs, and based on this information, the identification unit can provide a provenance fingerprint for the call. Based on the call provenance fingerprint, the detection system can identify, verify, or provide forensic information about a call audio source.Type: ApplicationFiled: June 3, 2021Publication date: September 23, 2021Inventors: Vijay BALASUBRAMANIYAN, Mustaque AHAMAD, Patrick Gerard TRAYNOR, Michael Thomas HUNTER, Aamir POONAWALLA
-
Patent number: 11050876Abstract: Various embodiments of the invention are detection systems and methods for detecting call provenance based on call audio. An exemplary embodiment of the detection system can comprise a characterization unit, a labeling unit, and an identification unit. The characterization unit can extract various characteristics of networks through which a call traversed, based on call audio. The labeling unit can be trained on prior call data and can identify one or more codecs used to encode the call, based on the call audio. The identification unit can utilize the characteristics of traversed networks and the identified codecs, and based on this information, the identification unit can provide a provenance fingerprint for the call. Based on the call provenance fingerprint, the detection system can identify, verify, or provide forensic information about a call audio source.Type: GrantFiled: December 30, 2019Date of Patent: June 29, 2021Assignee: Georgia Tech Research CorporationInventors: Vijay Balasubramaniyan, Mustaque Ahamad, Patrick Gerard Traynor, Michael Thomas Hunter, Aamir Poonawalla
-
Publication number: 20210150010Abstract: 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.Type: ApplicationFiled: January 25, 2021Publication date: May 20, 2021Inventors: Scott Strong, Kailash Patil, David Dewey, Raj Bandyopadhyay, Telvis Calhoun, Vijay Balasubramaniyan
-
Patent number: 10902105Abstract: 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.Type: GrantFiled: July 18, 2019Date of Patent: January 26, 2021Assignee: Pindrop Security, Inc.Inventors: Scott Strong, Kailash Patil, David Dewey, Raj Bandyopadhyay, Telvis Calhoun, Vijay Balasubramaniyan
-
Publication number: 20200137222Abstract: Various embodiments of the invention are detection systems and methods for detecting call provenance based on call audio. An exemplary embodiment of the detection system can comprise a characterization unit, a labeling unit, and an identification unit. The characterization unit can extract various characteristics of networks through which a call traversed, based on call audio. The labeling unit can be trained on prior call data and can identify one or more codecs used to encode the call, based on the call audio. The identification unit can utilize the characteristics of traversed networks and the identified codecs, and based on this information, the identification unit can provide a provenance fingerprint for the call. Based on the call provenance fingerprint, the detection system can identify, verify, or provide forensic information about a call audio source.Type: ApplicationFiled: December 30, 2019Publication date: April 30, 2020Inventors: Vijay BALASUBRAMANIYAN, Mustaque AHAMAD, Patrick Gerard TRAYNOR, Michael Thomas HUNTER, Aamir POONAWALLA
-
Patent number: 10523809Abstract: Various embodiments of the invention are detection systems and methods for detecting call provenance based on call audio. An exemplary embodiment of the detection system can comprise a characterization unit, a labeling unit, and an identification unit. The characterization unit can extract various characteristics of networks through which a call traversed, based on call audio. The labeling unit can be trained on prior call data and can identify one or more codecs used to encode the call, based on the call audio. The identification unit can utilize the characteristics of traversed networks and the identified codecs, and based on this information, the identification unit can provide a provenance fingerprint for the call. Based on the call provenance fingerprint, the detection system can identify, verify, or provide forensic information about a call audio source.Type: GrantFiled: November 9, 2016Date of Patent: December 31, 2019Assignee: Georgia Tech Research CorporationInventors: Vijay Balasubramaniyan, Mustaque Ahamad, Patrick Gerard Traynor, Michael Thomas Hunter, Aamir Poonawalla
-
Publication number: 20190342452Abstract: 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.Type: ApplicationFiled: July 18, 2019Publication date: November 7, 2019Inventors: Scott STRONG, Kailash PATIL, David DEWEY, Raj BANDYOPADHYAY, Telvis CALHOUN, Vijay BALASUBRAMANIYAN
-
Patent number: 10362172Abstract: 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.Type: GrantFiled: January 25, 2018Date of Patent: July 23, 2019Assignee: Pindrop Security, Inc.Inventors: Scott Strong, Kailash Patil, David Dewey, Raj Bandyopadhyay, Telvis Calhoun, Vijay Balasubramaniyan
-
Publication number: 20180152561Abstract: 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.Type: ApplicationFiled: January 25, 2018Publication date: May 31, 2018Applicant: PINDROP SECURITY, INC.Inventors: Scott STRONG, Kailash PATIL, David DEWEY, Raj BANDYOPADHYAY, Telvis CALHOUN, Vijay BALASUBRAMANIYAN
-
Patent number: 9930186Abstract: 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.Type: GrantFiled: October 14, 2016Date of Patent: March 27, 2018Assignee: PINDROP SECURITY, INC.Inventors: Raj Bandyopadhyay, Kailash Patil, David Dewey, Scott Strong, Telvis Calhoun, Vijay Balasubramaniyan
-
Patent number: 9883040Abstract: 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.Type: GrantFiled: October 14, 2016Date of Patent: January 30, 2018Assignee: PINDROP SECURITY, INC.Inventors: Scott Strong, Kailash Patil, David Dewey, Raj Bandyopadhyay, Telvis Calhoun, Vijay Balasubramaniyan
-
Publication number: 20170126884Abstract: Various embodiments of the invention are detection systems and methods for detecting call provenance based on call audio. An exemplary embodiment of the detection system can comprise a characterization unit, a labeling unit, and an identification unit. The characterization unit can extract various characteristics of networks through which a call traversed, based on call audio. The labeling unit can be trained on prior call data and can identify one or more codecs used to encode the call, based on the call audio. The identification unit can utilize the characteristics of traversed networks and the identified codecs, and based on this information, the identification unit can provide a provenance fingerprint for the call. Based on the call provenance fingerprint, the detection system can identify, verify, or provide forensic information about a call audio source.Type: ApplicationFiled: November 9, 2016Publication date: May 4, 2017Applicant: Georgia Tech Research CorporationInventors: Vijay BALASUBRAMANIYAN, Mustaque AHAMAD, Patrick Gerard TRAYNOR, Michael Thomas HUNTER, Aamir POONAWALLA
-
Publication number: 20170111506Abstract: 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.Type: ApplicationFiled: October 14, 2016Publication date: April 20, 2017Applicant: PINDROP SECURITY, INC.Inventors: Scott STRONG, Kailash PATIL, David DEWEY, Raj BANDYOPADHYAY, Telvis CALHOUN, Vijay BALASUBRAMANIYAN
-
Publication number: 20170111515Abstract: 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.Type: ApplicationFiled: October 14, 2016Publication date: April 20, 2017Applicant: PINDROP SECURITY, INC.Inventors: Raj BANDYOPADHYAY, Kailash PATIL, David DEWEY, Scott STRONG, Telvis CALHOUN, Vijay BALASUBRAMANIYAN
-
Patent number: 9516497Abstract: Various embodiments of the invention are detection systems and methods for detecting call provenance based on call audio. An exemplary embodiment of the detection system can comprise a characterization unit, a labeling unit, and an identification unit. The characterization unit can extract various characteristics of networks through which a call traversed, based on call audio. The labeling unit can be trained on prior call data and can identify one or more codecs used to encode the call, based on the call audio. The identification unit can utilize the characteristics of traversed networks and the identified codecs, and based on this information, the identification unit can provide a provenance fingerprint for the call. Based on the call provenance fingerprint, the detection system can identify, verify, or provide forensic information about a call audio source.Type: GrantFiled: May 18, 2015Date of Patent: December 6, 2016Assignee: GEORGIA TECH RESEARCH CORPORATIONInventors: Vijay Balasubramaniyan, Mustaque Ahamad, Patrick Gerard Traynor, Michael Thomas Hunter, Aamir Poonawalla
-
Publication number: 20150257001Abstract: Various embodiments of the invention are detection systems and methods for detecting call provenance based on call audio. An exemplary embodiment of the detection system can comprise a characterization unit, a labeling unit, and an identification unit. The characterization unit can extract various characteristics of networks through which a call traversed, based on call audio. The labeling unit can be trained on prior call data and can identify one or more codecs used to encode the call, based on the call audio. The identification unit can utilize the characteristics of traversed networks and the identified codecs, and based on this information, the identification unit can provide a provenance fingerprint for the call. Based on the call provenance fingerprint, the detection system can identify, verify, or provide forensic information about a call audio source.Type: ApplicationFiled: May 18, 2015Publication date: September 10, 2015Inventors: Vijay Balasubramaniyan, Mustaque Ahamad, Patrick Gerard Traynor, Michael Thomas Hunter, Aamir Poonawalla