Abstract: A computer-implemented system and method relate to certified defense against adversarial patch attacks. A set of one-mask images is generated using a first mask at a set of predetermined regions of a source image. The source image is obtained from a sensor. A set of one-mask predictions is generated, via a machine learning system, based on the set of one-mask images. A first one-mask image is extracted from the set of one-mask images. The first one-mask image is associated with a first one-mask prediction that is identified as a minority amongst the set of one-mask predictions. A set of two-mask images is generated by masking the first one-mask image using a set of second masks. The set of second masks include at least a first submask and a second submask in which a dimension of the first submask is less than a dimension of the first mask. A set of two-mask predictions is generated based on the set of two-mask images.

Abstract: A computer-implemented system and method relate to certified robust defenses against adversarial patches. A set of one-mask images are generated using a source image and a first mask at a set of predetermined image regions. The set of predetermined image regions collectively cover at least every pixel of the source image. A particular one-mask image with a highest prediction loss is selected from among the set of one-mask images. A set of two-mask images is generated using the selected one-mask image and a second mask at the set of predetermined image regions. A particular two-mask image with a highest prediction loss is selected from among the set of two-mask images. The machine learning system is trained using a training dataset, which includes the selected two-mask image.

Abstract: A computer-implemented system and method relate to certified robust defenses against adversarial patches. A two-mask image is generated using a first mask and a second mask with respect to a source image. The two-mask image is associated with a highest prediction loss. A set of two-submask images are generated using a first submask and a second submask with respect to the source image. The first submask refers to a portion of the first mask. The second submask refers a portion of the second mask. A machine learning system generates a set of predictions upon receiving the set of two-submask images. A particular two-submask image with a highest prediction loss is selected from among the set of two-submask images. The machine learning system is trained via a training dataset, which includes the source image, the two-mask image, and the selected two-submask image.

Abstract: A system and method include dividing a source image into a plurality of source regions, which are portions of the source image that correspond to a plurality of grid regions. A mask is used to create a first masked region that masks a first source region and a first unmasked region that comprises a second source region. A first inpainted region is generated by inpainting the first masked region based on the second source region. Similarity data is generated based on a similarity assessment. A protected image is generated that includes at least (i) the first masked region at a first grid region when the similarity data indicates that the first source region is not similar to the first inpainted region and (ii) the first inpainted region at the first grid region when the similarity data indicates that the first source region is similar to the first inpainted region.

Abstract: A computer-implemented system and method relate to certified defense against adversarial patch attacks. A set of one-mask images is generated using a first mask at a set of predetermined regions of a source image. The source image is obtained from a sensor. A set of one-mask predictions is generated, via a machine learning system, based on the set of one-mask images. A first one-mask image is extracted from the set of one-mask images. The first one-mask image is associated with a first one-mask prediction that is identified as a minority amongst the set of one-mask predictions. A set of two-mask images is generated by masking the first one-mask image using a set of second masks. The set of second masks include at least a first submask and a second submask in which a dimension of the first submask is less than a dimension of the first mask. A set of two-mask predictions is generated based on the set of two-mask images.