Adversarial Test on Learnable Image Encryption

MaungMaung, AprilPyone; Sirichotedumrong, Warit; Kiya, Hitoshi

doi:10.1109/gcce46687.2019.9015447

Cited by 9 publications

(1 citation statement)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The accuracy obtained for CIFAR-10 was 86.3% and that for CIFAR-100 was 56.8%, compared to 88.4% for CIFAR-10 and 59.1% for CIFAR-100 using plain images. Moreover, it provides robustness against adversarial attacks, where the images are designed to make the NN misclassify with high confidence [18]. However, the visual information of the encrypted images can be reconstructed using Generative Adversarial Network attack (GAN-attack) and Inverse Transformation Network attack (ITN-attack) [17].…”

Section: Tanaka's Schemementioning

confidence: 99%

Privacy-Preserving Deep Neural Network Methods: Computational and Perceptual Methods—An Overview

Saj

Gooya²,

Alfalou³

et al. 2021

Electronics

View full text Add to dashboard Cite

Privacy-preserving deep neural networks have become essential and have attracted the attention of many researchers due to the need to maintain the privacy and the confidentiality of personal and sensitive data. The importance of privacy-preserving networks has increased with the widespread use of neural networks as a service in unsecured cloud environments. Different methods have been proposed and developed to solve the privacy-preserving problem using deep neural networks on encrypted data. In this article, we reviewed some of the most relevant and well-known computational and perceptual image encryption methods. These methods as well as their results have been presented, compared, and the conditions of their use, the durability and robustness of some of them against attacks, have been discussed. Some of the mentioned methods have demonstrated an ability to hide information and make it difficult for adversaries to retrieve it while maintaining high classification accuracy. Based on the obtained results, it was suggested to develop and use some of the cited privacy-preserving methods in applications other than classification.

show abstract

Section: Tanaka's Schemementioning

confidence: 99%