A buyer-traceable DNN model IP protection method against piracy and misappropriation
Recently proposed model functionality and attribute extraction techniques have exacerbated unauthorized low-cost reproduction of deep neural network (DNN) models for similar applications. In particular, intellectual property (IP) theft and unauthorized distribution of DNN models by dishonest buyers...
Saved in:
Main Authors: | Wang, Si, Xu, Chaohui, Zheng, Yue, Chang, Chip Hong |
---|---|
Other Authors: | School of Electrical and Electronic Engineering |
Format: | Conference or Workshop Item |
Language: | English |
Published: |
2022
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/159395 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
A DNN fingerprint for non-repudiable model ownership identification and piracy detection
by: Zheng, Yue, et al.
Published: (2022) -
An imperceptible data augmentation based blackbox clean-label backdoor attack on deep neural networks
by: Xu, Chaohui, et al.
Published: (2024) -
Towards unbiased visual emotion recognition via causal intervention
by: Chen, Yuedong, et al.
Published: (2023) -
An empirical study of the inherent resistance of knowledge distillation based federated learning to targeted poisoning attacks
by: He, Weiyang, et al.
Published: (2024) -
Test optimization in DNN testing: A survey
by: HU, Qiang, et al.
Published: (2024)