EUVIMEDEUVIMED entdecken
Crossref

Perceptual Hashing of Deep Convolutional Neural Networks for Model Copy Detection

Haozhe Chen, Hang Zhou, Jie Zhang, Dongdong Chen, Weiming Zhang, Kejiang Chen, Gang Hua, Nenghai Yu

ACM Transactions on Multimedia Computing, Communications, and Applications · 31.05.2023 · 19 (3) · 1-20

DOI: 10.1145/3572777 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Multimedia Computing, Communications, and Applications, online erschienen am 02.03.2023. Verfasst von Haozhe Chen und 7 weiteren Autor:innen. Die Arbeit wurde bisher 30-mal zitiert (Crossref) und nennt 63 Literaturangaben. Gefördert von: Natural Science Foundation of China, Exploration Fund Project of University of Science and Technology of China, Fundamental Research Funds for the Central Universities.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In recent years, many model intellectual property (IP) proof methods for IP protection have been proposed, such as model watermarking and model fingerprinting. However, with the increasing number of models transmitted and deployed on the Internet, quickly finding the suspect model among thousands of models on model-sharing platforms such as GitHub is in great demand, which concurrently triggers the new security problem of model copy detection for IP protection. As an important part of the model IP protection system, the model copy detection task has not received enough attention. Due to the high computational complexity, both model watermarking and model fingerprinting lack the capability to efficiently find suspected infringing models among tens of millions of models. In this article, inspired by the hash-based image retrieval methods, we introduce a novel model copy detection mechanism: perceptual hashing for convolutional neural networks (CNNs). The proposed perceptual hashing algorithm can convert the weights of CNNs to fixed-length binary hash codes so that the lightly modified version has the similar hash code as the original model. By comparing the similarity of a pair of hash codes between a query model and a test model in the model library, similar versions of a query model can be retrieved efficiently. To the best of our knowledge, this is the first perceptual hashing algorithm for deep neural network models. Specifically, we first select the important model weights based on the model compression theory, then calculate the normal test statistics (NTS) on the segments of important weights, and finally encode the NTS features into hash codes. The experiment performed on a model library containing 3,565 models indicates that our perceptual hashing scheme has a superior copy detection performance.

Förderung

  • Natural Science Foundation of China
  • Exploration Fund Project of University of Science and Technology of China
  • Fundamental Research Funds for the Central Universities

Zitieren

APA

Chen, H., Zhou, H., Zhang, J., Chen, D., Zhang, W., Chen, K., Hua, G., & Yu, N. (2023). Perceptual Hashing of Deep Convolutional Neural Networks for Model Copy Detection. ACM Transactions on Multimedia Computing, Communications, and Applications, 19(3), 1-20. https://doi.org/10.1145/3572777

Vancouver

Chen H, Zhou H, Zhang J, Chen D, Zhang W, Chen K, et al. Perceptual Hashing of Deep Convolutional Neural Networks for Model Copy Detection. ACM Transactions on Multimedia Computing, Communications, and Applications. 2023;19(3):1-20. doi:10.1145/3572777

BibTeX
@article{Chen2023,
  author = {Chen, Haozhe and Zhou, Hang and Zhang, Jie and Chen, Dongdong and Zhang, Weiming and Chen, Kejiang and Hua, Gang and Yu, Nenghai},
  title = {Perceptual Hashing of Deep Convolutional Neural Networks for Model Copy Detection},
  journal = {ACM Transactions on Multimedia Computing, Communications, and Applications},
  year = {2023},
  volume = {19},
  number = {3},
  pages = {1--20},
  doi = {10.1145/3572777}
}
Kostenlos starten →