TP-CRIV: A Framework for Third-Party Challenge-Response Identity Verification of AI Models
TP-CRIV targets a third-party verification setting in which the verifier has neither white-box nor API access to the claimant's model, can interact with the suspicious deployed service only through its ordinary black-box inference interface, and does not require protocol-specific cooperation from the service provider.
Teruki Sano, Minoru Kuribayashi, Masao Sakai et al.
· IEEE Access · 0 citations