RIKEN Center for Advanced Intelligence Project AI Safety and Reliability Unit
Unit Leader: Hiromi Arai (Ph.D.)
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 Fields
Related Research Fields
- Computer Science
- Social Sciences
Papers with an asterisk(*) are based on research conducted outside of RIKEN.
Ulrich Aïvodji, Hiromi Arai, Olivier Fortineau, Sébastien Gambs, Satoshi Hara., and Alain Tapp.:
"Fairwashing: the risk of rationalization"
Proceedings of the 36th International Conference on Machine Learning, ICML 2019
Hiromi Arai, Keita Emura, and Takuya Hayashi.:
"A framework of privacy preserving anomaly detection: Providing traceability without big brother"
Proceedings of the 2017 Workshop on Privacy in the Electronic Society, co-located with CCS 2017
*Hiromi Arai, Jun Sakuma, and Koji Tsuda.:
"Quantifying Genomic Privacy in Genetic Test Results"
3rd International Workshop on Genome Privacy and Security
*Kentaro Minami, Hiromi Arai, Issei Sato,, and Hiroshi Nakagawa
"Differential Privacy without Sensitivity"
Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016
*Shimizu Kana et.al.,
"Privacy-Preserving Search for Chemical Compound Databases"
BMC bioinformatics 16.S18 (2015): S6.
- Hiromi Arai
- Unit Leader
Nihonbashi 1-chome Mitsui Building, 15th floor,
1-4-1 Nihonbashi,Chuo-ku, Tokyo 103-0027, Japan
Email: hiromi.arai [at] riken.jp