Abstract: A method of validating a defense mechanism of an artificial intelligence (“AI”) system includes defining an optimizing function for a mean and a variance of parameters of input queries. The method further includes applying a Bayesian optimization algorithm on the input queries in dependence of the optimizing function followed by a Gaussian process at least twice to create a posterior distribution for the mean and the variance of parameters to reverse engineer the AI system. The method also includes feeding the AI system with a set of the input queries whose mean and variance of parameters have a high probability in the posterior distribution, and recording an output of the AI system to validate the defense mechanism of the AI system.

Abstract: An AI system includes an input interface configured to receive input data from at least one user, and a blocker module configured (i) to detect the received input data is an attack input data, (ii) to manipulate output data of the blocker module, and (iii) to send the output data from the blocker module to the at least one user. The AI system further includes an AI module configured to process the input data received by the blocker module and to generate output data corresponding to the input data. The AI system also includes a blocker notification module configured to transmit a notification to the owner of the AI system on detecting an attack input data, and an output interface configured to send the generated output data to the at least one user.

Abstract: A method of training a submodule and preventing capture of an AI module is disclosed. Input data received from an input interface is transmitted through a blocker module to an AI module, which computes a first output data by executing a first model. A submodule in the AI system trained using methods steps processes the input data to identify an attack vector from the input data. The submodule executes the first model and at least a second model. The first model and the second model have a first and second set of network parameters and hyper-parameters respectively. The identification information of the attack vector is sent to the information gain module.

Abstract: A method of training a submodule and preventing capture of an AI module is disclosed. Input data is received from at least one user through an input interface. It is transmitted through a blocker module to an AI module which computes a first output data by executing a first model based on the input data. Input data is pre-processed by a submodule to obtain at least one subset of the input data. This submodule is trained using methods steps. The input data and the at least one subset of the input data are processed by the submodule to identify an attack vector from the input data. The identification information of the attack vector is sent to the information gain module.

Abstract: A method of training a submodule and preventing capture of an AI module is disclosed. Input data is received from at least one user through an input interface. It is transmitted through a blocker module to an AI module, which computes a first output data by executing a first model based on the input data. Input data is pre-processed by a submodule to obtain at least one subset of the input data. This submodule is trained using methods steps. The input data and the at least one subset of the input data are processed by the submodule to identify an attack vector from the input data. The identification information of the attack vector is sent to the information gain module.

Abstract: An AI system includes an input interface configured to receive input data from at least one user, and a blocker module configured (i) to detect the received input data is an attack input data, (ii) to manipulate output data of the blocker module, and (iii) to send the output data from the blocker module to the at least one user. The AI system further includes an AI module configured to process the input data received by the blocker module and to generate output data corresponding to the input data. The AI system also includes a blocker notification module configured to transmit a notification to the owner of the AI system on detecting an attack input data, and an output interface configured to send the generated output data to the at least one user.