paper-with-me

Papers

Adversarial Test on Learnable Image Encryption

2019-07-31 · MaungMaung AprilPyone, Warit Sirichotedumrong, Hitoshi Kiya

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.

📄 PDF Abstract BibTeX arXiv:1907.13342

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial RobustnessPrivacy Preserving

Similar Papers 제목 키워드 기반

An Overview of Compressible and Learnable Image Transformation with Secret Key and Its Applications

2022-01-26 · Hitoshi Kiya, AprilPyone MaungMaung, Yuma Kinoshita, Shoko Imaizumi 외

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 Preserving

Attack GAN (AGAN ): A new Security Evaluation Tool for Perceptual Encryption

2024-07-09 · Umesh Kashyap, Sudev Kumar Padhi, Sk. Subidh Ali

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 Network

Learnable Image Encryption

2018-03-19 · Masayuki Tanaka

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 Learning

Generative Model-Based Attack on Learnable Image Encryption for Privacy-Preserving Deep Learning

2023-03-09 · AprilPyone MaungMaung, Hitoshi Kiya

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 Learning

Adversarial Defense via Image Denoising with Chaotic Encryption

2022-03-19 · Shi Hu, Eric Nalisnick, Max Welling

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