NEURAL NETWORK FRAGILE WATERMARKING WITH NO MODEL PERFORMANCE DEGRADATION

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

20 Scopus citations

Abstract

Deep neural networks are vulnerable to malicious fine-tuning attacks such as data poisoning and backdoor attacks. Therefore, in recent research, it is proposed how to detect malicious fine-tuning of neural network models. However, it usually negatively affects the performance of the protected model. Thus, we propose a novel neural network fragile watermarking with no model performance degradation. In the process of watermarking, we train a generative model with the specific loss function and secret key to generate triggers that are sensitive to the fine-tuning of the target classifier. In the process of verifying, we adopt the watermarked classifier to get labels of each fragile trigger. Then, malicious fine-tuning can be detected by comparing secret keys and labels. Experiments on classic datasets and classifiers show that the proposed method can effectively detect model malicious fine-tuning with no model performance degradation.

Original languageEnglish
Title of host publication2022 IEEE International Conference on Image Processing, ICIP 2022 - Proceedings
PublisherIEEE Computer Society
Pages3958-3962
Number of pages5
ISBN (Electronic)9781665496209
DOIs
StatePublished - 2022
Event29th IEEE International Conference on Image Processing, ICIP 2022 - Bordeaux, France
Duration: 16 Oct 202219 Oct 2022

Publication series

NameProceedings - International Conference on Image Processing, ICIP
ISSN (Print)1522-4880

Conference

Conference29th IEEE International Conference on Image Processing, ICIP 2022
Country/TerritoryFrance
CityBordeaux
Period16/10/2219/10/22

Keywords

  • Backdoor attack
  • Fragile watermarking
  • Malicious tuning detection
  • Model integrity protection
  • Neural network

Fingerprint

Dive into the research topics of 'NEURAL NETWORK FRAGILE WATERMARKING WITH NO MODEL PERFORMANCE DEGRADATION'. Together they form a unique fingerprint.

Cite this