US Patent:
20190220605, Jul 18, 2019
Inventors:
- Santa Clara CA, US
Antonios Papadimitriou - Maplewood NJ, US
Anindya Paul - Hillsboro OR, US
Micah Sheller - Hillsboro OR, US
Li Chen - Hillsboro OR, US
Cory Cornelius - Portland OR, US
Brandon Edwards - Portland OR, US
Assignee:
Intel Corporation - Santa Clara CA
International Classification:
G06F 21/60
G06N 3/04
G06N 3/08
Abstract:
In one example an apparatus comprises a memory and a processor to create, from a first deep neural network (DNN) model, a first plurality of DNN models, generate a first set of adversarial examples that are misclassified by the first plurality of deep neural network (DNN) models, determine a first set of activation path differentials between the first plurality of adversarial examples, generate, from the first set of activation path differentials, at least one composite adversarial example which incorporates at least one intersecting critical path that is shared between at least two adversarial examples in the first set of adversarial examples, and use the at least one composite adversarial example to generate a set of inputs for a subsequent training iteration of the DNN model. Other examples may be described.