EM-ID: tag-less identification of electrical devices via electromagnetic emissions

Patent metadata

Field	Value
Publication number	US-10366118-B2
Application number	US-201715462457-A
Country	US
Kind code	B2
Filing date	Mar 17, 2017
Priority date	Mar 17, 2016
Publication date	Jul 30, 2019
Grant date	Jul 30, 2019

Abstract

A technique for identifying individual instances of electronic devices. This is done by using a basic RFID reader to read the RF emissions from the electronic device to obtain an emitted electromagnetic spectrum and compare it to a library of emitted electromagnetic spectrums of different instances of that type of electronic device and, based on that comparison, finding a best match and identifying the electronic device as being a particular instance of that type of electronic device. This comparison may be made by computing Euclidean distances between vectors that are based on the measured electromagnetic spectrums.

First claim

We claim:

1. A method for identifying a particular instance of an electronic device, the method comprising:
receiving a spectrum of electromagnetic signals emitted by an electronic device under examination;
after the receiving, determining a category classification of the electronic device based on the received spectrum of electromagnetic signals;
after the determining, comparing the received spectrum of electromagnetic signals to a library of spectrums of electromagnetic signals for electronic devices belonging to the category classification, each of the spectrums of electromagnetic signals in the library representing the spectrum of electromagnetic signals produced by a particular instance of an electronic device belonging to the category classification;
finding a best match of the received spectrum of electromagnetic signals to one of the spectrums of electromagnetic signals in the library; and
identifying the electronic device under examination as the electronic device in the library that produces the spectrum of electromagnetic signals to which the best match was made.

2. A method as defined in claim 1 , wherein the comparing and finding operations include converting the spectrum of electromagnetic signals emitted by the electronic device under examination to a first vector and computing the Euclidean distance from the first vector to a plurality of vectors that each correspond to one of the spectrums of electromagnetic signals in the library.

3. A method as defined in claim 1 , wherein the receiving operation includes providing an antenna and amplifying signals detected by the antenna.

4. A method as defined in claim 1 , wherein the received spectrum includes the portion of the electromagnetic spectrum up to 1 MHz.

5. A method as defined in claim 1 , wherein the received spectrum includes the portion of the electromagnetic spectrum up to 500 kHz.

6. A method as defined in claim 1 , wherein the received spectrum includes the portion of the electromagnetic spectrum up to 200 kHz.

7. A method as defined in claim 1 , wherein the received spectrum includes the portion of the electromagnetic spectrum up to 100 MHz.

8. A method as defined in claim 1 , wherein the received spectrum includes the portion of the electromagnetic spectrum up to 20 kHz.

9. A method as defined in claim 1 , wherein the received spectrum includes the portion of the electromagnetic spectrum up to 10 kHz.

10. A method as defined in claim 1 , wherein the received spectrum includes the portion of the electromagnetic spectrum up to 5 kHz.

11. A method as defined in claim 1 , wherein the received spectrum includes the portion of the electromagnetic spectrum up to 3 kHz.

12. The method of claim 1 , wherein the spectrum of electromagnetic signals is converted into an electromagnetic identification (EM-ID) and wherein the finding the best match comprises using a cosine similarity function to rank similarity between the EM-ID and representations of the spectrums of the electromagnetic signals in the library.

13. The method of claim 12 , wherein the EM-ID is a vector and wherein the representations in the library are vectors.

14. The method of claim 12 , wherein the similarity rank is used to determine the best match as having a highest probability match.

15. The method of claim 1 , wherein the determining of the category classification of the electronic device comprising using a cosine similarity function to rank a plurality of potential category classifications for the electronic device based on the received spectrum of electromagnetic signals.

16. The method of claim 15 , wherein the received spectrum of electromagnetic signals is converted to a vector prior to the using of the cosine similarity function.

17. The method of claim 1 , wherein the category classification defines a model of a device produced by a manufacturer or distributed by a distributor.

18. A method comprising:
separately for each of a group of electronic devices of the same type, receiving the spectrum of electromagnetic signals emitted by each electronic device in the group;
creating a library of the received spectrums, including an indication of which electromagnetic device in the group produced each spectrum;
after the creating of the library, receiving a spectrum of electromagnetic signals emitted by an electronic device that is powered on;
comparing the received spectrum of electromagnetic signals to the library of spectrums of electromagnetic signals using a cosine similarity function;
finding a best match of the received spectrum of electromagnetic signals to one of the spectrums of electromagnetic signals in the library based on rankings from the cosine similarity function; and
identifying the electronic device under examination as the electronic device in the library that produces the spectrum of electromagnetic signals to which the best match was made.

19. A method as defined in claim 18 , wherein the comparing and finding operations include converting the spectrum of electromagnetic signals emitted by the electronic device under examination to a first vector and computing the Euclidean distance from the first vector to a plurality of vectors that each correspond to one of the spectrums of electromagnetic signals in the library.

20. A method as defined in claim 18 , wherein the receiving operation includes providing an antenna and amplifying signals detected by the antenna.

21. A method as defined in claim 18 , wherein the received spectrum includes the portion of the electromagnetic spectrum up to 1 MHz.

22. A method as defined in claim 18 , wherein the received spectrum includes the portion of the electromagnetic spectrum up to 500 kHz.

23. A method as defined in claim 18 , wherein the received spectrum includes the portion of the electromagnetic spectrum up to 200 kHz.

24. A method as defined in claim 18 , wherein the received spectrum includes the portion of the electromagnetic spectrum up to 100 MHz.

25. A method as defined in claim 18 , wherein the received spectrum includes the portion of the electromagnetic spectrum up to 20 kHz.

26. A method as defined in claim 18 , wherein the received spectrum includes the portion of the electromagnetic spectrum up to 10 kHz.

27. The method of claim 18 , further comprising, prior to the comparing step, classifying the electronic device emitting the received electromagnetic emissions into a category and wherein the spectrums in the library are each associated with an electronic device belonging to the category.

28. The method of claim 27 , wherein, prior to the comparing, the received spectrum is converted into a vector and wherein the received spectrums in the library are represented as vectors.

29. The method of claim 27 , wherein the similarity rank is used to determine the best match as having a highest probability match.

30. A method for identifying a particular instance of an electronic device, the method comprising:
receiving an electromagnetic signal emitted by an electronic device whenever the electronic device is powered on;
after the receiving, determining a category classification of the electronic device based on the received electromagnetic signal by using a cosine similarity function to score comparisons of the received electromagnetic signals and representations of electromagnetic signals stored in two or more

Assignees

• Disney Entpr Inc

Inventors

• Sample Alanson
• Yang Chouchang

Classifications

• G06F16/211

  Schema design and management · CPC title

• G06F16/381 Primary

  using identifiers, e.g. barcodes, RFIDs (for URLs G06F16/9554) · CPC title

• G06F16/334

  Query execution (filtering based on additional data G06F16/335) · CPC title