Process to make machine object detection robust to adversarial attacks

A computer program product for object detection that is robust to adversarial attacks, the computer program product comprising:

• a non-transitory computer-readable medium having executable instructions encoded thereon, such that upon execution of the instructions by one or more processors, the one or more processors perform operations of:
• generating an initial hypothesis of an identity of an object in an input image using a sparse convolutional neural network (CNN) and a distribution aware classifier;
• performing a foveated hypothesis verification process, wherein performing the foveated hypothesis verification process comprises identifying a region of the input image that supports the initial hypothesis;
• using a part-based classifier, predicting an identity of a part of the object in the region of the input image;
• determining an attack probability for the predicted identity of the part;
• updating the initial hypothesis based on the predicted identity of the part and the attack probability;
• performing the foveated hypothesis verification process and updating of hypotheses until a hypothesis reaches a certainty threshold;
• labeling the object based on the hypothesis that reached the certainty threshold;
• and
• controlling an action performed by an autonomous platform based on the labeling of the object.

A computer implemented method for object detection that is robust to adversarial attacks, the method comprising an act of:

• causing one or more processers to execute instructions encoded on a non-transitory computer-readable medium, such that upon execution, the one or more processors perform operations of:
• generating an initial hypothesis of an identity of an object in an input image using a sparse convolutional neural network (CNN) and a distribution aware classifier;
• performing a foveated hypothesis verification process, wherein performing the foveated hypothesis verification process comprises identifying a region of the input image that supports the initial hypothesis;
• using a part-based classifier, predicting an identity of a part of the object in the region of the input image;
• determining an attack probability for the predicted identity of the part;
• updating the initial hypothesis based on the predicted identity of the part and the attack probability;
• performing the foveated hypothesis verification process and updating of hypotheses until a hypothesis reaches a certainty threshold;
• labeling the object based on the hypothesis that reached the certainty threshold;
• and
• controlling an action performed by an autonomous platform based on the labeling of the object.