| CPC G06F 21/55 (2013.01) | 18 Claims |
|
1. A defender module for detecting adversarial Artificial Intelligence (AI) attacks at a trained AI agent that is communicatively coupled to the defender module, the defender module comprising:
a processing unit; and
a non-transitory media readable by the processing unit, the media storing instructions that when executed by the processing unit causes the processing unit to:
acquire and store input data provided to the trained AI agent together with output data generated by the trained AI agent based on the input data provided to the trained AI agent;
retrieve a baseline quantum state lattice matrix that was generated based on ground truth inputs provided to the trained AI agent and ground truth outputs generated by the trained AI agent for each of the ground truth inputs provided to the trained AI agent, and wherein each of the generated ground truth outputs comprises a plurality of outcomes inferred by the trained AI agent and probability amplitudes associated with each of the plurality of outcomes;
generate an output quantum state based on the acquired output data, wherein the acquired output data comprises a plurality of outcomes inferred by the trained AI agent for the acquired input data and probability amplitudes associated with each of the plurality of outcomes;
generate a quantum state for each row in the baseline quantum state lattice matrix; and
perform a quantum-based anomaly classification of the acquired data based on the generated output quantum state, and the quantum states generated for each row in the baseline quantum state lattice matrix.
|