Abstract: One embodiment provides a method, including: assigning a machine learning model signature to a machine learning model, wherein the machine learning model signature is generated using (i) data points and (ii) corresponding data labels from training data; receiving input comprising identification of a target machine learning model; acquiring a target signature for the target machine learning model by generating a signature for the target machine learning model using (i) data points from the assigned machine learning model signature and (ii) labels assigned to those data points by the target machine learning model; determining a stolen score by comparing the target signature to the machine learning model signature and identifying the number of data labels that match between the target signature and the machine learning model signature; and classifying the target machine learning model as stolen based upon the stolen score reaching a predetermined threshold.

Abstract: One embodiment provides a method for delaying malicious attacks on machine learning models that a trained using input captured from a plurality of users, including: deploying a model, said model designed to be used with an application, for responding to requests received from users, wherein the model comprises a machine learning model that has been previously trained using a data set; receiving input from one or more users; determining, using a malicious input detection technique, if the received input comprises malicious input; if the received input comprises malicious input, removing the malicious input from the input to be used to retrain the model; retraining the model using received input that is determined to not be malicious input; and providing, using the retrained model, a response to a received user query, the retrained model delaying the effect of malicious input on provided responses by removing malicious input from retraining input.

Abstract: One embodiment provides a method for delaying malicious attacks on machine learning models that a trained using input captured from a plurality of users, including: deploying a model, said model designed to be used with an application, for responding to requests received from users, wherein the model comprises a machine learning model that has been previously trained using a data set; receiving input from one or more users; determining, using a malicious input detection technique, if the received input comprises malicious input; if the received input comprises malicious input, removing the malicious input from the input to be used to retrain the model; retraining the model using received input that is determined to not be malicious input; and providing, using the retrained model, a response to a received user query, the retrained model delaying the effect of malicious input on provided responses by removing malicious input from retraining input.

Abstract: One embodiment provides a method, including: assigning a machine learning model signature to a machine learning model, wherein the machine learning model signature is generated using (i) data points and (ii) corresponding data labels from training data; receiving input comprising identification of a target machine learning model; acquiring a target signature for the target machine learning model by generating a signature for the target machine learning model using (i) data points from the assigned machine learning model signature and (ii) labels assigned to those data points by the target machine learning model; determining a stolen score by comparing the target signature to the machine learning model signature and identifying the number of data labels that match between the target signature and the machine learning model signature; and classifying the target machine learning model as stolen based upon the stolen score reaching a predetermined threshold.

Abstract: A method, system and computer program product are disclosed for candidate screening. In one embodiment, the method comprises identifying a multitude of dimensions of a specified job, assigning a weight to each of the dimensions, and determining whether each of a group of candidate satisfies the weights assigned to the dimensions. In an embodiment, a score is assigned to each candidate based on the weights assigned to the dimensions, and the number of the candidates score above a threshold is determined. In an embodiment, if the number of the candidates that have a score above the threshold is less than a defined number, one or more of the weights is adjusted, and the candidates are rescored based on these adjusted weights. In embodiments of the invention, the weights are adjusted based on the number of the candidates that score above the threshold, or based on the other weights.