Granted Patent B1

US 10,225,277 · App. 16/004,267 · Granted Mar 5, 2019

Abstract

Claims (54)

1. A computer-implemented method for verifying that influence of a user data point has been removed from a machine learning classifier, at least a portion of the method being performed by a network device comprising one or more processors, the method comprising:

training, by a network device, a machine learning classifier using a training set of data points that includes a user data point;

receiving, at the network device, a request to remove the influence of the user data point from the machine learning classifier;

calculating, by the network device, a first loss of the machine learning classifier;

updating, by the network device, the machine learning classifier by updating parameters of the machine learning classifier to remove influence of the user data point using an influence function without retraining the machine learning classifier;

calculating, by the network device, a second loss of the machine learning classifier;

calculating, by the network device using an influence function, an expected difference in loss of the machine learning classifier due to removal of the influence of the user data point from the machine learning classifier;

verifying that the influence of the user data point has been removed from the machine learning classifier by determining, by the network device, that the difference between the first loss and the second loss is within a threshold of the expected difference in loss;

receiving, at the network device from a second network device, a model inversion attack against the machine learning classifier; and

thwarting, at the network device, the model inversion attack against the machine learning classifier, due to the updated parameters of the machine learning classifier, to protect the user data point from being exposed by the model inversion attack.

2. The method of claim 1 , wherein the machine learning classifier is one or more of a Logistic Regression (LR) classifier, a Linear Support Vector Machine (LSVM) classifier, and a Multi-Layer Perceptron (MLP) classifier.

3. The method of claim 1 , wherein the user data point comprises personally identifiable information of an individual inside the European Union.

4. The method of claim 3 , wherein the request is received pursuant to the European Union General Data Protection Regulation (GDPR).

5. The method of claim 1 , wherein the model inversion attack is received via application programming interface (API) queries.

6. The method of claim 5 , wherein the machine learning classifier is exposed to the API as a Machine Learning as a Service (MLaaS) offering to enable API queries against the machine learning classifier.

7. The method of claim 1 , further comprising:

sending, from the network device and to a second network device, verification that the influence of the user data point has been removed from the machine learning classifier.

8. One or more non-transitory computer-readable media comprising one or more computer-readable instructions that, when executed by one or more processors of a network device, cause the network device to perform a method for verifying that influence of a user data point has been removed from a machine learning classifier, the method comprising:

training, by a network device, a machine learning classifier using a training set of data points that includes a user data point;

receiving, at the network device, a request to remove the influence of the user data point from the machine learning classifier;

calculating, by the network device, a first loss of the machine learning classifier;

updating, by the network device, the machine learning classifier by updating parameters of the machine learning classifier to remove influence of the user data point using an influence function without retraining the machine learning classifier;

calculating, by the network device, a second loss of the machine learning classifier;

calculating, by the network device using an influence function, an expected difference in loss of the machine learning classifier due to removal of the influence of the user data point from the machine learning classifier; and

verifying that the influence of the user data point has been removed from the machine learning classifier by determining, by the network device, that the difference between the first loss and the second loss is within a threshold of the expected difference in loss;

receiving, at the network device from a second network device, a model inversion attack against the machine learning classifier; and

thwarting, at the network device, the model inversion attack against the machine learning classifier, due to the updated parameters of the machine learning classifier, to protect the user data point from being exposed by the model inversion attack.

9. The one or more non-transitory computer-readable media of claim 8 , wherein the machine learning classifier is one or more of a Logistic Regression (LR) classifier, a Linear Support Vector Machine (LSVM) classifier, and a Multi-Layer Perceptron (MLP) classifier.

10. The one or more non-transitory computer-readable media of claim 8 , wherein the user data point comprises personally identifiable information of an individual inside the European Union.

11. The one or more non-transitory computer-readable media of claim 10 , wherein the request is received pursuant to the European Union General Data Protection Regulation (GDPR).

12. The one or more non-transitory computer-readable media of claim 8 , wherein the model inversion attack is received via application programming interface (API) queries.

13. The one or more non-transitory computer-readable media of claim 12 , wherein the machine learning classifier is exposed to the API as a Machine Learning as a Service (MLaaS) offering to enable API queries against the machine learning classifier.

14. The one or more non-transitory computer-readable media of claim 8 , further comprising:

sending, from the network device and to a second network device, verification that the influence of the user data point has been removed from the machine learning classifier.

15. A network device comprising:

one or more processors; and

one or more non-transitory computer-readable media comprising one or more computer-readable instructions that, when executed by the one or more processors, cause the network device to perform a method for verifying that influence of a user data point has been removed from a machine learning classifier, the method comprising:

training, by a network device, a machine learning classifier using a training set of data points that includes a user data point;

receiving, at the network device, a request to remove the influence of the user data point from the machine learning classifier;

calculating, by the network device, a first loss of the machine learning classifier;

updating, by the network device, the machine learning classifier by updating parameters of the machine learning classifier to remove influence of the user data point using an influence function without retraining the machine learning classifier;

calculating, by the network device, a second loss of the machine learning classifier;

calculating, by the network device using an influence function, an expected difference in loss of the machine learning classifier due to removal of the influence of the user data point from the machine learning classifier;

verifying that the influence of the user data point has been removed from the machine learning classifier by determining, by the network device, that the difference between the first loss and the second loss is within a threshold of the expected difference in loss;

receiving, at the network device from a second network device, a model inversion attack against the machine learning classifier; and

thwarting, at the network device, the model inversion attack against the machine learning classifier, due to the updated parameters of the machine learning classifier, to protect the user data point from being exposed by the model inversion attack.

16. The network device of claim 15 , wherein the machine learning classifier is one or more of a Logistic Regression (LR) classifier, a Linear Support Vector Machine (LSVM) classifier, and a Multi-Layer Perceptron (MLP) classifier.

17. The network device of claim 15 , wherein:

the user data point comprises personally identifiable information of an individual inside the European Union; and

the request is received pursuant to the European Union General Data Protection Regulation (GDPR).

18. The network device of claim 15 , wherein the model inversion attack is received via application programming interface (API) queries.

19. The network device of claim 18 , wherein the machine learning classifier is exposed to the API as a Machine Learning as a Service (MLaaS) offering to enable API queries against the machine learning classifier.

20. The network device of claim 15 , further comprising:

sending, from the network device and to a second network device, verification that the influence of the user data point has been removed from the machine learning classifier.

Assignments (6)