Systems and methods for detecting call provenance from call audio

Patent metadata

Field	Value
Publication number	US-10523809-B2
Application number	US-201615347440-A
Country	US
Kind code	B2
Filing date	Nov 9, 2016
Priority date	Jun 29, 2010
Publication date	Dec 31, 2019
Grant date	Dec 31, 2019

Abstract

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.

First claim

What is claimed is:

1. A computer implemented method, comprising:
receiving, for a first call placed from a first communications device to a second communications device, data representing call audio received at the first communications device during the first call;
detecting, based on the data representing the call audio received at the first communications device, a degradation imparted to the data by one or more networks traversed by the first call; and
predicting the one or more networks traversed by the first call based on the degradation.

2. The computer implemented method according to claim 1 , further comprising:
identifying, based on the degradation, a provenance of the first call.

3. The computer implemented method according to claim 1 ,
wherein the one or more networks traversed by the first call includes an encoder or a decoder that respectively encodes or decodes the data, and
wherein the degradation includes an encoder or decoder artifact introduced by the encoder or decoder.

4. The computer implemented method according to claim 1 ,
wherein the one or more networks traversed by the first call includes a packet loss concealment algorithm that respectively conceals packet losses in the data, and
wherein the degradation includes concealed packet loss introduced by the packet loss concealment algorithm.

5. The computer implemented method according to claim 1 ,
wherein the degradation includes packet loss suffered by the data as the data traverses the one or more networks.

6. The computer implemented method according to claim 1 ,
wherein the degradation includes a bit error suffered by the data as the data traverses the one or more networks.

7. The computer implemented method according to claim 1 , wherein the detecting and predicting steps are performed during the first call.

8. The computer implemented method according to claim 1 , further comprising:
receiving metadata associated with the first call,
said predicting step identifying the provenance of the first call based on the degradation and the metadata.

9. A computer implemented method, comprising:
receiving, for a first call placed from a first communications device to a second communications device, data representing call audio received at the first communications device during the first call;
detecting, based on the data representing the call audio received at the first communications device, a degradation imparted to the data by one or more networks traversed by the first call; and
predicting an identity of the first communications device based on the degradation.

10. The computer implemented method of claim 9 , said verification step including:
determining a feature profile of the first call based on the degradation; and
classifying the feature profile of the first call based at least in part on a plurality of feature profiles of previous calls.

11. The computer implemented method of claim 9 , further comprising:
receiving metadata associated with the first communications device,
wherein said classifying step limits the classification based on the metadata.

12. The computer implemented method of claim 9 , further comprising:
determining a plurality of provenance fingerprints for a plurality of calls, each provenance fingerprint being based on one or more predetermined characteristics detected in audio from an associated call, and each provenance fingerprint uniquely identifying at least a portion of a path of the associated call; and
compiling the plurality of provenance fingerprints into an exclusion list.

13. The computer implemented method of claim 12 , the exclusion list being a blacklist.

14. The computer implemented method of claim 12 , the exclusion list being a whitelist.

15. The computer implemented method of claim 9 , further comprising:
determining a plurality of provenance fingerprints for a plurality of calls, each provenance fingerprint being based on characteristics detected in audio from an associated call, and each provenance fingerprint uniquely identifying an associated call source; and
compiling the plurality of provenance fingerprints into a fraud database.

16. The computer implemented method of claim 15 , further comprising:
determining a first provenance fingerprint for the first audio from the first call, wherein the provenance fingerprint is based on one or more characteristics of the audio from the first call and uniquely identifies the at least a portion of the path of the first call;
matching the first provenance fingerprint to at least one of the plurality of provenance fingerprints in the fraud database; and
providing a notification based on the matching.

Assignees

• Georgia Tech Res Inst

Inventors

• Balasubramaniyan Vijay
• Ahamad Mustaque
• Traynor Patrick Gerard
• Hunter Michael Thomas
• Poonawalla Aamir

Classifications

• H04L65/1076 Primary

  Screening of IP real time communications, e.g. spam over Internet telephony [SPIT] · CPC title

• H04M1/68

  Circuit arrangements for preventing eavesdropping · CPC title

• H04W12/12

  Detection or prevention of fraud · CPC title

• H04M3/2281 Primary

  Call monitoring, e.g. for law enforcement purposes; Call tracing; Detection or prevention of malicious calls · CPC title

• H04W12/02

  Protecting privacy or anonymity, e.g. protecting personally identifiable information [PII] · CPC title