ZKROWNN: Zero Knowledge Right of Ownership for Neural Networks. (arXiv:2309.06779v1 [cs.CR])

Training contemporary AI models requires investment in procuring learning
data and computing resources, making the models intellectual property of the
owners. Popular model watermarking solutions rely on key input triggers for
detection; the keys have to be kept private to prevent discovery, forging, and
removal of the hidden signatures. We present ZKROWNN, the first automated
end-to-end framework utilizing Zero-Knowledge Proofs (ZKP) that enable an
entity to validate their ownership of a model, while preserving the privacy of
the watermarks. ZKROWNN …

ai models computing data detection discovery hidden input intellectual property investment key keys knowledge making networks neural networks ownership popular private property resources signatures solutions training watermarking zero knowledge