Next Article in Journal
A Bivariate Power Lindley Survival Distribution
Next Article in Special Issue
A Novel Deep Learning Zero-Watermark Method for Interior Design Protection Based on Image Fusion
Previous Article in Journal
Nested Sentiment Analysis for ESG Impact: Leveraging FinBERT to Predict Market Dynamics Based on Eco-Friendly and Non-Eco-Friendly Product Perceptions with Explainable AI
Previous Article in Special Issue
Towards Discriminability with Distribution Discrepancy Constrains for Multisource Domain Adaptation
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

TraceGuard: Fine-Tuning Pre-Trained Model by Using Stego Images to Trace Its User

by
Limengnan Zhou
1,†,
Xingdong Ren
2,†,
Cheng Qian
2 and
Guangling Sun
2,*
1
School of Electronic and Information Engineering, University of Electronic Science and Technology of China, Zhongshan Institute, Zhongshan 528402, China
2
School of Communication and Information Engineering, Shanghai University, Shanghai 200444, China
*
Author to whom correspondence should be addressed.
These authors contributed equally to this work.
Mathematics 2024, 12(21), 3333; https://doi.org/10.3390/math12213333
Submission received: 20 September 2024 / Revised: 15 October 2024 / Accepted: 22 October 2024 / Published: 24 October 2024
(This article belongs to the Special Issue Mathematics Methods in Image Processing and Computer Vision)

Abstract

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 service (MLaaS). Some malicious users have pre-trained models illegally to redeploy them and earn money. However, most of the current methods focus on verifying the copyright of the model rather than tracing responsibility for the suspect model. In this study, TraceGuard is proposed, the first framework based on steganography for tracing a suspect self-supervised learning (SSL) pre-trained model, to ascertain which authorized user illegally released the suspect model or if the suspect model is independent. Concretely, the framework contains an encoder and decoder pair and the SSL pre-trained model. Initially, the base pre-trained model is frozen, and the encoder and decoder are jointly learned to ensure the two modules can embed the secret key into the cover image and extract the secret key from the embedding output by the base pre-trained model. Subsequently, the base pre-trained model is fine-tuned using stego images to implement a fingerprint while the encoder and decoder are frozen. To assure the effectiveness and robustness of the fingerprint and the utility of fingerprinted pre-trained models, three alternate steps of model stealing simulations, fine-tuning for uniqueness, and fine-tuning for utility are designed. Finally, the suspect pre-trained model is traced to its user by querying stego images. Experimental results demonstrate that TraceGuard can reliably trace suspect models and is robust against common fingerprint removal attacks such as fine-tuning, pruning, and model stealing. In the future, we will further improve the robustness against model stealing attack.
Keywords: intellectual property protection; tracing pre-trained model; fine-tuning pre-trained model; steganography network; stego image; fingerprint removal attack intellectual property protection; tracing pre-trained model; fine-tuning pre-trained model; steganography network; stego image; fingerprint removal attack

Share and Cite

MDPI and ACS Style

Zhou, L.; Ren, X.; Qian, C.; Sun, G. TraceGuard: Fine-Tuning Pre-Trained Model by Using Stego Images to Trace Its User. Mathematics 2024, 12, 3333. https://doi.org/10.3390/math12213333

AMA Style

Zhou L, Ren X, Qian C, Sun G. TraceGuard: Fine-Tuning Pre-Trained Model by Using Stego Images to Trace Its User. Mathematics. 2024; 12(21):3333. https://doi.org/10.3390/math12213333

Chicago/Turabian Style

Zhou, Limengnan, Xingdong Ren, Cheng Qian, and Guangling Sun. 2024. "TraceGuard: Fine-Tuning Pre-Trained Model by Using Stego Images to Trace Its User" Mathematics 12, no. 21: 3333. https://doi.org/10.3390/math12213333

APA Style

Zhou, L., Ren, X., Qian, C., & Sun, G. (2024). TraceGuard: Fine-Tuning Pre-Trained Model by Using Stego Images to Trace Its User. Mathematics, 12(21), 3333. https://doi.org/10.3390/math12213333

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop