Picture for Kazuhiro Takemoto

Kazuhiro Takemoto

Large-scale moral machine experiment on large language models

Add code
Nov 11, 2024
Viaarxiv icon

All in How You Ask for It: Simple Black-Box Method for Jailbreak Attacks

Add code
Jan 22, 2024
Viaarxiv icon

The Moral Machine Experiment on Large Language Models

Add code
Sep 12, 2023
Viaarxiv icon

Simple black-box universal adversarial attacks on medical image classification based on deep neural networks

Add code
Aug 11, 2021
Figure 1 for Simple black-box universal adversarial attacks on medical image classification based on deep neural networks
Figure 2 for Simple black-box universal adversarial attacks on medical image classification based on deep neural networks
Figure 3 for Simple black-box universal adversarial attacks on medical image classification based on deep neural networks
Figure 4 for Simple black-box universal adversarial attacks on medical image classification based on deep neural networks
Viaarxiv icon

Vulnerability of deep neural networks for detecting COVID-19 cases from chest X-ray images to universal adversarial attacks

Add code
May 22, 2020
Figure 1 for Vulnerability of deep neural networks for detecting COVID-19 cases from chest X-ray images to universal adversarial attacks
Figure 2 for Vulnerability of deep neural networks for detecting COVID-19 cases from chest X-ray images to universal adversarial attacks
Figure 3 for Vulnerability of deep neural networks for detecting COVID-19 cases from chest X-ray images to universal adversarial attacks
Figure 4 for Vulnerability of deep neural networks for detecting COVID-19 cases from chest X-ray images to universal adversarial attacks
Viaarxiv icon

Simple iterative method for generating targeted universal adversarial perturbations

Add code
Nov 18, 2019
Figure 1 for Simple iterative method for generating targeted universal adversarial perturbations
Figure 2 for Simple iterative method for generating targeted universal adversarial perturbations
Figure 3 for Simple iterative method for generating targeted universal adversarial perturbations
Figure 4 for Simple iterative method for generating targeted universal adversarial perturbations
Viaarxiv icon