Network Identification
2 papers with code • 0 benchmarks • 0 datasets
Identification of parameters composing a neural network. Also referred as model stealing attack or parameter reverse engineering.
Benchmarks
These leaderboards are used to track progress in Network Identification
Most implemented papers
Beyond Data Samples: Aligning Differential Networks Estimation with Scientific Knowledge
Learning the differential statistical dependency network between two contexts is essential for many real-life applications, mostly in the high dimensional low sample regime.
Expand-and-Cluster: Parameter Recovery of Neural Networks
flavio-martinelli/expand-and-cluster
•
•
Can we identify the weights of a neural network by probing its input-output mapping?
