Dual Graphs of Polyhedral Decompositions for the Detection of Adversarial Attacks. (arXiv:2211.13305v1 [cs.CV])

Previous work has shown that a neural network with the rectified linear unit
(ReLU) activation function leads to a convex polyhedral decomposition of the
input space. These decompositions can be represented by a dual graph with
vertices corresponding to polyhedra and edges corresponding to polyhedra
sharing a facet, which is a subgraph of a Hamming graph. This paper illustrates
how one can utilize the dual graph to detect and analyze adversarial attacks in
the context of digital images. When an …

adversarial attacks detection