Kazuhiro Takemoto
Relevante Arbeiten
Meistzitierte Publikationen im Bereich Gesundheit & MedTech
Vulnerability of deep neural networks for detecting COVID-19 cases from chest X-ray images to universal adversarial attacks
2020 · 57 Zit. · PLoS ONE
Revisiting the political biases of ChatGPT
2023 · 41 Zit. · Frontiers in Artificial Intelligence
The moral machine experiment on large language models
2024 · 37 Zit. · Royal Society Open Science
Backdoor Attacks to Deep Neural Network-Based System for COVID-19 Detection from Chest X-ray Images
2021 · 15 Zit. · Applied Sciences
The Moral Machine Experiment on Large Language Models
2023 · 9 Zit. · PubMed
Large-scale moral machine experiment on large language models
2025 · 5 Zit. · PLoS ONE
Revisiting the Political Biases of ChatGPT
2023 · 0 Zit. · Preprints.org
Revisiting the Political Biases of ChatGPT
2023 · 0 Zit. · Preprints.org
Adversarial vulnerability assessment of vision language models for healthcare
2025 · 0 Zit. · Briefings in Bioinformatics
All in How You Ask for It: Simple Black-Box Method for Jailbreak Attacks
2024 · 0 Zit. · arXiv (Cornell University)
Playing Prisoner's Dilemma Games with a Large Language Model
2025 · 0 Zit. · SSRN Electronic Journal
Revisiting the Political Biases of ChatGPT
2023 · 0 Zit. · Preprints.org