[PDF][PDF] An overview of compressible and learnable image transformation with secret key and its applications
This article presents an overview of image transformation with a secret key and its
applications. Image transformation with a secret key enables us not only to protect visual …
applications. Image transformation with a secret key enables us not only to protect visual …
Deep intellectual property protection: A survey
Deep Neural Networks (DNNs), from AlexNet to ResNet to ChatGPT, have made
revolutionary progress in recent years, and are widely used in various fields. The high …
revolutionary progress in recent years, and are widely used in various fields. The high …
A protection method of trained CNN model with a secret key from unauthorized access
In this paper, we propose a novel method for protecting convolutional neural network
models with a secret key set so that unauthorized users without the correct key set cannot …
models with a secret key set so that unauthorized users without the correct key set cannot …
Wide flat minimum watermarking for robust ownership verification of gans
We propose a novel multi-bit box-free watermarking method for the protection of Intellectual
Property Rights (IPR) of GANs with improved robustness against white-box model-level …
Property Rights (IPR) of GANs with improved robustness against white-box model-level …
[HTML][HTML] TraceGuard: Fine-Tuning Pre-Trained Model by Using Stego Images to Trace Its User
L Zhou, X Ren, C Qian, G Sun - Mathematics, 2024 - mdpi.com
Currently, a significant number of pre-trained models are published online to provide
services to users owing to the rapid maturation and popularization of machine learning as a …
services to users owing to the rapid maturation and popularization of machine learning as a …
A Robust DCT-Based Scheme for Watermarking Deep Neural Networks
This paper proposes a new robust scheme to provide copy protection services to Deep
Nural Network (DNN) models using digital watermarks. The rationale of the proposed …
Nural Network (DNN) models using digital watermarks. The rationale of the proposed …
ActiveGuard: An active intellectual property protection technique for deep neural networks by leveraging adversarial examples as users' fingerprints
The intellectual properties (IP) protection of deep neural networks (DNN) models has raised
many concerns in recent years. To date, most of the existing works use DNN watermarking …
many concerns in recent years. To date, most of the existing works use DNN watermarking …
[PDF][PDF] Access control of semantic segmentation models using encrypted feature maps
In this paper, we propose an access control method with a secret key for semantic
segmentation models for the first time so that unauthorized users without a secret key cannot …
segmentation models for the first time so that unauthorized users without a secret key cannot …
Protecting IP of deep neural networks with watermarking using logistic disorder generation trigger sets
H Lin, S Shen, H Lyu - Multimedia Tools and Applications, 2024 - Springer
As deep learning technology matures, it's being widely deployed in fields like image
classification and speech recognition. However, training a functional deep learning model …
classification and speech recognition. However, training a functional deep learning model …
Transfer learning-based model protection with secret key
We propose a novel method for protecting trained models with a secret key so that
unauthorized users without the correct key cannot get the correct inference. By taking …
unauthorized users without the correct key cannot get the correct inference. By taking …