Hitoshi Kiya

Difficulty in estimating visual information from randomly sampled images

2020

In this paper, we evaluate dimensionality reduction methods in terms of difficulty in estimating visual information on original images from dimensionally reduced ones. Recently, dimensionality reduction has been receiving attention as the process of not …

Block Scrambling Image Encryption Used in Combination with Data Augmentation for Privacy-Preserving DNNs

2021

In this paper, we propose a novel learnable image encryption method for privacy-preserving deep neural networks (DNNs). The proposed method is carried out on the basis of block scrambling used in combination with data augmentation …

Ensemble of Key-Based Models: Defense Against Black-Box Adversarial Attacks

2021 · 2021 IEEE 10th Global Conference on Consumer Electronics (GCCE)

We propose a voting ensemble of models trained by using block-wise transformed images with secret keys against black-box attacks. Although key-based adversarial defenses were effective against gradient-based (white-box) attacks, they cannot defend against gradient-free (black-box) …

Hindering Adversarial Attacks with Multiple Encrypted Patch Embeddings

2023 · arXiv (Cornell University)

In this paper, we propose a new key-based defense focusing on both efficiency and robustness. Although the previous key-based defense seems effective in defending against adversarial examples, carefully designed adaptive attacks can bypass the previous …