InverseNet

InverseNet, developed by researchers including Xueluan Gong, is a benchmark and attack framework that measures AI vulnerability to hardware mismatches and augments model extraction with data inversion techniques.

Two-hop subgraph: this entity, every entity it directly relates to, and every entity those neighbors relate to. Drag a node, scroll to zoom, click to inspect — or click any neighbor and re-center the atlas there.