A DNN fingerprint for non-repudiable model ownership identification and piracy detection

• المؤلفون الرئيسيون: Zheng, Yue, Wang, Si, Chang, Chip Hong
• مؤلفون آخرون: School of Electrical and Electronic Engineering
• التنسيق: مقال
• اللغة: English
• منشور في: 2022
• الموضوعات: Engineering::Electrical and electronic engineering; DNN IP Protection; Fingerprinting; Random Projection; Cross Application; Ownership
• الوصول للمادة أونلاين: https://hdl.handle.net/10356/162779

A high-performance Deep Neural Network (DNN) model is a valuable intellectual property (IP) since designing and training such a model from scratch is very costly. Model transfer learning, compression and retraining are commonly used by pirates to evade detection or even redeploy the pirated models f...