Adversarial Test on Learnable Image Encryption
Data for deep learning should be protected for privacy preserving. Researchers have come up with the notion of learnable image encryption to satisfy the requirement. However, existing privacy preserving approaches have never considered the threat of adversarial attacks. In this paper, we ran an adversarial test on learnable image encryption in five different scenarios. The results show different behaviors of the network in the variable key scenarios and suggest learnable image encryption provides certain level of adversarial robustness.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial RobustnessPrivacy PreservingSimilar Papers 제목 키워드 기반
An Overview of Compressible and Learnable Image Transformation with Secret Key and Its Applications
This article presents an overview of image transformation with a secret key and its applications. Image transformation with a secret key enables us not only to protect visual information on plain images but also to embed…
BIG-bench Machine LearningPrivacy PreservingAttack GAN (AGAN ): A new Security Evaluation Tool for Perceptual Encryption
Training state-of-the-art (SOTA) deep learning models requires a large amount of data. The visual information present in the training data can be misused, which creates a huge privacy concern. One of the prominent soluti…
Generative Adversarial NetworkLearnable Image Encryption
The network-based machine learning algorithm is very powerful tools. However, it requires huge training dataset. Researchers often meet privacy issues when they collect image dataset especially for surveillance applicati…
BIG-bench Machine LearningGenerative Model-Based Attack on Learnable Image Encryption for Privacy-Preserving Deep Learning
In this paper, we propose a novel generative model-based attack on learnable image encryption methods proposed for privacy-preserving deep learning. Various learnable encryption methods have been studied to protect the s…
Privacy PreservingPrivacy Preserving Deep LearningAdversarial Defense via Image Denoising with Chaotic Encryption
In the literature on adversarial examples, white box and black box attacks have received the most attention. The adversary is assumed to have either full (white) or no (black) access to the defender's model. In this work…
Adversarial DefenseDenoisingImage Denoising