EUVIMEDEUVIMED entdecken
Crossref

Privacy-Preserving Image Retrieval in Cloud Computing via Adaptive Secret Keys and Self-Supervised Block-Augmented Pretraining

Qihua Feng, Zhixun Lu, Litian Zhang, Chaozhuo Li, Feiran Huang, Jian Weng, Philip S. Yu

IEEE Transactions on Services Computing · 2025-07 · 18 (4) · 2310-2325

DOI: 10.1109/tsc.2025.3576692 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Services Computing, 2025-07. Verfasst von Qihua Feng und 6 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 82 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Science and Technology Major Project of Tibetan Autonomous Region of China, Open Research Fund of Machine Learning and Cyber Security Interdiscipline Research Engineering Center of Jiangsu Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Privacy-Preserving Image Retrieval (PPIR) enables searching for similar images on cloud servers while safeguarding image privacy. PPIR uploads encrypted images to servers to address privacy concerns and then employs deep neural networks for retrieval on extracted features from cipher-images. However, current PPIR encrypts all images with the same secret keys to maintain consistent feature spaces, lacking support for adaptive keys where distinct images are encrypted with various keys. To this end, we propose a new PPIR scheme to support adaptive keys while keeping stable feature spaces. Specifically, we design ingenious image encryption to align with feature extraction during the JPEG compression process, incorporating encryptable orthogonal transformations, shuffling, stream cipher, and sign encryption operations. Our approach extracts well-designed absolute value sequences of local blocks and global histogram features from cipher-images, ensuring stable feature spaces under adaptive keys. To enhance model generalization performance, we employ Self-Supervised Contrastive Learning (SSCL) to build a pretraining model and propose a straightforward yet efficient block-sampling augmentation technique for the structured features to drive SSCL. Moreover, our retrieval model implements a dual-attention structure to capture dependencies among local block sequences and import scores of global features. Extensive experiments on four datasets demonstrate that our approach achieves superior retrieval accuracy compared to existing schemes and maintains excellent retrieval performance under adaptive keys, effectively preserving image privacy.

Förderung

  • National Natural Science Foundation of China
  • Science and Technology Major Project of Tibetan Autonomous Region of China
  • Open Research Fund of Machine Learning and Cyber Security Interdiscipline Research Engineering Center of Jiangsu Province
  • National Joint Engineering Research Center of Network Security Detection and Protection Technology
  • Guangdong Key Laboratory of Data Security and Privacy Preserving
  • Guangdong Hong Kong Joint Laboratory for Data Security and Privacy Protection
  • Engineering Research Center of Trustworthy AI
  • Ministry of Education

Zitieren

APA

Feng, Q., Lu, Z., Zhang, L., Li, C., Huang, F., Weng, J., & Yu, P. S. (2025). Privacy-Preserving Image Retrieval in Cloud Computing via Adaptive Secret Keys and Self-Supervised Block-Augmented Pretraining. IEEE Transactions on Services Computing, 18(4), 2310-2325. https://doi.org/10.1109/tsc.2025.3576692

Vancouver

Feng Q, Lu Z, Zhang L, Li C, Huang F, Weng J, et al. Privacy-Preserving Image Retrieval in Cloud Computing via Adaptive Secret Keys and Self-Supervised Block-Augmented Pretraining. IEEE Transactions on Services Computing. 2025;18(4):2310-2325. doi:10.1109/tsc.2025.3576692

BibTeX
@article{Feng2025,
  author = {Feng, Qihua and Lu, Zhixun and Zhang, Litian and Li, Chaozhuo and Huang, Feiran and Weng, Jian and Yu, Philip S.},
  title = {Privacy-Preserving Image Retrieval in Cloud Computing via Adaptive Secret Keys and Self-Supervised Block-Augmented Pretraining},
  journal = {IEEE Transactions on Services Computing},
  year = {2025},
  volume = {18},
  number = {4},
  pages = {2310--2325},
  doi = {10.1109/tsc.2025.3576692}
}
Kostenlos starten →