Misuse index for explainable artificial intelligence in computing environments
A mechanism is described for facilitating misuse index for explainable artificial intelligence in computing environments, according to one embodiment. A method of embodiments, as described herein, includes mapping training data with inference uses in a machine learning environment, where the training data is used for training a machine learning model. The method may further include detecting, based on one or more policy/parameter thresholds, one or more discrepancies between the training data and the inference uses, classifying the one or more discrepancies as one or more misuses, and creating a misuse index listing the one or more misuses.
1. A method for machine learning, comprising:
determining whether there is any misuse of a machine learning model associated with an inference of the machine learning model based on training data and inference data, wherein the machine learning model is trained with the training data, and the inference of the machine learning model is based on the inference data;
after determining that there is a misuse, determining a misuse index value for the misuse based on the inference; and
evaluating, based on the misuse index value, a severity of the misuse of the machine learning model.
2. The method of claim 1 , wherein determining where there is any misuse of the machine learning model comprises:
detecting one or more discrepancies between the training data and the inference data.
3. The method of claim 1 , wherein determining whether there is any misuse of the machine learning model comprises:
determining whether there is any misuse of the machine learning model further based on metadata associated with the training data.
4. The method of claim 1 , wherein determining the misuse index value for the misuse comprises:
performing a plurality of inferences of the machine learning model using the inference data, the plurality of inferences comprising the inference; and
determining the misuse index value for the misuse based on the plurality of inferences, the misuse index value meeting a confidence level.
5. The method of claim 4 , wherein each of the plurality of inferences comprises inputting the inference data into the machine learning model.
6. The method of claim 1 , wherein evaluating the severity of the misuse of the machine learning model comprises:
performing a comparison of the misuse index value with one or more threshold values; and
evaluating the severity based on a result of the comparison.
7. The method of claim 1 , further comprising:
mitigating the misuse of the machine learning model by:
forming new training data, wherein a feature is better represented by the new training data than the training data, and
training the machine learning model with the new training data.
8. One or more non-transitory computer-readable media storing instructions executable to perform operations for machine learning, the operations comprising:
determining whether there is any misuse of a machine learning model associated with an inference of the machine learning model based on training data and inference data, wherein the machine learning model is trained with the training data, and the inference of the machine learning model is based on the inference data;
after determining that there is a misuse, determining a misuse index value for the misuse based on the inference; and
evaluating, based on the misuse index value, a severity of the misuse of the machine learning model.
9. The one or more non-transitory computer-readable media of claim 8 , wherein determining where there is any misuse of the machine learning model comprises:
detecting one or more discrepancies between the training data and the inference data.
10. The one or more non-transitory computer-readable media of claim 8 , wherein determining whether there is any misuse of the machine learning model comprises:
determining whether there is any misuse of the machine learning model further based on metadata associated with the training data.
11. The one or more non-transitory computer-readable media of claim 8 , wherein determining the misuse index value for the misuse comprises:
performing a plurality of inferences of the machine learning model using the inference data, the plurality of inferences comprising the inference; and
determining the misuse index value for the misuse based on the plurality of inferences, the misuse index value meeting a confidence level.
12. The one or more non-transitory computer-readable media of claim 11 , wherein each of the plurality of inferences comprises inputting the inference data into the machine learning model.
13. The one or more non-transitory computer-readable media of claim 8 , wherein evaluating the severity of the misuse of the machine learning model comprises:
performing a comparison of the misuse index value with one or more threshold values; and
evaluating the severity based on a result of the comparison.
14. The one or more non-transitory computer-readable media of claim 8 , wherein the operations further comprise:
mitigating the misuse of the machine learning model by:
forming new training data, wherein a feature is better represented by the new training data than the training data, and
training the machine learning model with the new training data.
15. An apparatus, comprising:
a computer processor for executing computer program instructions; and
a non-transitory computer-readable memory storing computer program instructions executable by the computer processor to perform operations comprising:
determining whether there is any misuse of a machine learning model associated with an inference of the machine learning model based on training data and inference data, wherein the machine learning model is trained with the training data, and the inference of the machine learning model is based on the inference data,
after determining that there is a misuse, determining a misuse index value for the misuse based on the inference, and
evaluating, based on the misuse index value, a severity of the misuse of the machine learning model.
16. The apparatus of claim 15 , wherein determining where there is any misuse of the machine learning model comprises:
detecting one or more discrepancies between the training data and the inference data.
17. The apparatus of claim 15 , wherein determining whether there is any misuse of the machine learning model comprises:
determining whether there is any misuse of the machine learning model further based on metadata associated with the training data.
18. The apparatus of claim 15 , wherein determining the misuse index value for the misuse comprises:
performing a plurality of inferences of the machine learning model using the inference data, the plurality of inferences comprising the inference; and
determining the misuse index value for the misuse based on the plurality of inferences, the misuse index value meeting a confidence level.
19. The apparatus of claim 15 , wherein evaluating the severity of the misuse of the machine learning model comprises:
performing a comparison of the misuse index value with one or more threshold values; and
evaluating the severity based on a result of the comparison.
20. The apparatus of claim 15 , wherein the operations further comprise:
mitigating the misuse of the machine learning model by:
forming new training data, wherein a feature is better represented by the new training data than the training data, and
training the machine learning model with the new training data.