Steganographic passport: an owner and user verifiable credential for deep model IP protection without retraining

• Main Authors: Cui, Qi, Meng, Ruohan, Xu, Chaohui, Chang, Chip Hong
• Other Authors: School of Electrical and Electronic Engineering
• Format: Conference or Workshop Item
• Language: English
• Published: 2025
• Subjects: Computer and Information Science; Deep Learning; Artificial Intelligence; AI as a service; AI security
• Online Access: https://hdl.handle.net/10356/182742
• Institution: Nanyang Technological University

Ensuring the legal usage of deep models is crucial to promoting trustable accountable and responsible artificial intelligence innovation. Current passport-based methods that obfuscate model functionality for license-to-use and ownership verifications suffer from capacity and quality constraints as t...