Hiromi Arai
Hiromi Arai (Ph.D.)
Title
Unit Leader

Members

  • Unit leader
    Hiromi Arai
  • Visiting scientist
    Hisashi Kashima
  • Visiting scientist
    Satoshi Oyama
  • Visiting scientist
    Yukino Baba
  • Visiting scientist
    Yu Izumi
  • Visiting scientist
    Tetsushi Ohki
  • Visiting scientist
    Akira Kanaoka
  • Visiting scientist
    Yusuke Yamamoto
  • Visiting scientist
    Kyohei Atarashi
  • Visiting scientist
    Yuko Tanaka
  • Visiting scientist
    Tsubasa Takahashi

Introduction

Along with the widespread use of artificial intelligence technologies, there are increasing demands for safety and reliability of artificial intelligence, including transparency, fairness, accountability, and privacy. We aim to develop fundamental technologies to enhance the safety and reliability of AI. We also conduct interdisciplinary researches on these topics in collaboration with various fields such as computer science, social sciences, and humanities.

Main Research Field
Computer Science / Social Science and General
Research Field
AI Safety and Reliability / Privacy Preserving Technologies
Research Subjects
Fairness in AI, Explainable AI
Secure Computation, Differential Privacy
Analysis of Fake News and Abusive Languages
RIKEN Website URL
https://www.riken.jp/en/research/labs/aip/ai_soc/ai_saf_rely/index.html

Introduction Video

AI Safety and Reliability Unit (PI: Hiromi Arai)　 thumbnails
Show details
Poster(s)

Research Achievements

List of Achievements

Related posts

posted on March 27, 2025 11:09Information
[In the Media] Fairness and Social Bias in AI (SmartNews Media Research Institute, March 26, 2025)
posted on October 9, 2024 23:11Information
[Event report: ECCV 2024 Workshop] The Dark Side of Generative AIs and Beyond（Sep. 29, 2024, MiCo Milano, Italy)
posted on September 27, 2024 17:29Information
"Women in Tech 30" (Forbes Japan, November 2024 Issue)
posted on July 25, 2024 12:11Information
[Event Information]2024 Summer AI Seminar for the Next Generation (Middle School, High School, and Technical College Students) (July 27 – August 21)
posted on June 18, 2024 13:22Seminar
[ECCV 2024 Workshop] The Dark Side of Generative AIs and Beyond（Sep. 29, 2024, MiCo Milano, Italy)
posted on December 29, 2023 09:40Information
【In the media】Predicting Traffic Congestion with AI, a Countermeasure for the 24-year Logistics Problem (NIKKEI mornign edition, NIKKEI, December 27, 2023)
posted on December 15, 2023 10:39Information
11 papers were accepted at AAAI-24
posted on August 8, 2023 11:04Information
【In the media】QTNet: Theory-based Queue Length Prediction for Urban Traffic (NIKKEI, August 7, 2023)
posted on September 25, 2023 20:05Information
35 papers were accepted at NeurIPS 2023
posted on August 1, 2023 13:50Information
3 papers were accepted at KDD 2023
posted on July 21, 2023 09:36Information
7 papers have been accepted at ICCV 2023
posted on May 15, 2023 21:09
The 5th Annual Meeting of Japanese Associatin for Medical Artificial Intelligence (JMAI)
posted on May 9, 2023 17:54InformationPressrelease
【Press Release】Who Does Not Benefit from Fact-Checking Websites? A Psychological Characteristic
posted on May 2, 2023 09:42Information
23 papers have been accepted at ICML 2023
posted on October 31, 2022 12:03Information
The 3rd Japanese-German-French AI Symposium (Miraikan in Tokyo, Oct 27-28, 2022)
posted on July 26, 2022 13:27Information
The 4th Annual Meeting of Japanese Associatin for Medical Artificial Intelligence (JMAI)
posted on March 28, 2022 19:26Information
The Fifth AI Ethics meeting (the AI Ethics commitee, Seisen Junior & Senior High School)
posted on October 8, 2021 16:33Information
17 papers were accepted at NeurIPS 2021
posted on April 28, 2021 06:52Seminar
[25th AIP Open Seminar] Talks by AI Safety and Reliability Unit
posted on November 24, 2020 12:14Award
ARAI Hiromi Unit Leader et al. received CSS2020 Distinguished Paper Award