Hiromi Arai, Ph.D
Unit Leader, AI Safety and Reliability Unit, RIKEN AIP
cResearch interests: trustworthy AI, AI security and privacy, fairness in machine learning, explainable AI.
contact: hiromi( d o t )arai( a t m a r k )riken( d o t )jp
Research Map http://researchmap.jp/hiroara/
Google Scholar https://scholar.google.co.jp/citations?user=hllqYyQAAAAJ&hl=ja
DPLP http://www.informatik.uni-trier.de/~ley/pers/hd/a/Arai:Hiromi
[Publications]
Journal Articles
Hiromi Arai, Keita Emura, and Takuya Hayashi, "Privacy-Preserving Data Analysis: Providing Traceability without Big Brother", IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, Vol.104-A, No.1, pp.2-19, 2021.
TOMAŠEV, Nenad, et al. AI for social good: unlocking the opportunity for positive impact. Nature Communications, 2020, 11.1: 1-6.
Takuma Nakagawa, Hiromi Arai, Hiroshi Nakagawa, Personalized Anonymization for Set-Valued Data by Partial Suppression, Transactions on Data Privacy, Vol.11, Issue 3, pp.219-237, 2018.
Kana Shimizu, Koji Nuida, Hiromi Arai, Shigeo Mitsunari, Nuttapong Attrapadung, Michiaki Hamada, Koji Tsuda, Takatsugu Hirokawa, Jun Sakuma, Goichiro Hanaoka, Kiyoshi Asai. Privacy-Preserving Search for Chemical Compound Databases, BMC Bioinformatics, Vol. 16, Suppl. 18, S6, 2015.
Hiromi Arai, Keita Emura, Takahiro Matsuda. Anonymous Data Collection System with Mediators, International Conference on Cryptography and Information Security in the Balkans, Springer International Publishing, pp.141-160, 2014.
Hiroshi Kajino, Hiromi Arai, Hisashi Kashima. Preserving Worker Privacy in Crowdsourcing. Data Mining and Knowledge Discovery, Vol.28, Issue 5, pp.1314-1335, 2014.
Hiromi Arai, Satoru Watanabe, Takanori Kigawa, and Masayuki Yamamura, A new modeling method in feature construction for the HSQC spectra screening problem., Bioinformatics, Vol. 25, No. 7, pp. 948-953, 2009 (ISI Impact factor 4.328 (2009))
International Conference Papers (Peer-reviewed)
Mingzhe Yang, Hiromi Arai, Naomi Yamashita, Yukino Baba, Fair Machine Guidance to Enhance Fair Decision Making in Biased People, Proceedings of the CHI Conference on Human Factors in Computing Systems (CHI2024), 2024, 285, 1-18.
Yuko Tanaka, Miwa Inuzuka, Hiromi Arai, Yoichi Takahashi, Minao Kukita, Kentaro Inui, Who Does Not Benefit from Fact-checking Websites? A Psychological Characteristic Predicts the Selective Avoidance of Clicking Uncongenial Facts, Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems (CHI2023), 2023, 664, 1-17.
Ryuichiro Hataya, Han Bao, Hiromi Arai, Will Large-scale Generative Models Corrupt Future Datasets?, Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 20555-20565.
Yuko Tanaka, Hiromi Arai, Miwa Inuzuka, Yoichi Takahashi, Minao Kukita, Kentaro Inui, Fight Bias with Bias? Two Interventions for Mitigating the Selective Avoidance of Clicking Uncongenial Facts, Proceedings of the Annual Meeting of the Cognitive Science Society (CogSci), 2023, 45.
Ulrich Aïvodji, Hiromi Arai, Sébastien Gambs, Satoshi Hara, Characterizing the risk of fairwashing. Advances in Neural Information Processing Systems (NeurIPS2021), 2021, 34, 14822-14834.
Ulrich Aïvodji, Hiromi Arai, Olivier Fortineau, Sébastien Gambs, Satoshi Hara, Alain Tapp, Fairwashing: the risk of rationalization, Proceedings of the 36th International Conference on Machine Learning (ICML 2019), Long Beach, USA, 2019.
Hiromi Arai, Keita Emura, Takuya Hayashi, A Framework of Privacy Preserving Anomaly Detection: Providing Traceability without Big Brother, Proceedings of the 2017 on Workshop on Privacy in the Electronic Society (WPES2017), Dallas, USA, 2017.
Hiromi Arai, Jun Sakuma, Koji Tsuda. Quantifying Genomic Privacy in Genetic Test Results, 2nd International Workshop on Genome Privacy and Security (GenoPri’ 16), Chicago, USA, 2016.
Kentaro Minami, Hiromi Arai, Issei Sato, Hiroshi Nakagawa. Differential Privacy without Sensitivity, In Proceedings of the Advances in Neural Information Processing Systems (NIPS 2016), Barcelona, Spain, 2016.
Kentaro Minami, Hiromi Arai, Issei Sato. (ε,δ)-Differential Privacy of Gibbs Posteriors, NIPS 2015 Workshop on Learning and Privacy with Incomplete Data and Weak Supervision, Montreal, Canada, 2015.
Hiromi Arai and Jun Sakuma, Privacy Preserving Semi-Supervised Learning for Labeled Graphs, Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECMLPKDD 2011), pp.124-139 (2011). (Acceptance Rate 20%)
Jun Sakuma and Hiromi Arai, Online Prediction with Privacy, Proceedings of the 27th International Conference on Machine Learning (ICML 2010), pp.935-942 (2010) (Acceptance Rate 25.92%)
Hiromi Arai, Naoya Tochio, Tsuyoshi Kato, Takanori Kigawa, and Masayuki Yamamura, An accurate prediction method for protein structural class from signal patterns of NMR spectra in the absence of chemical shift assignments, Proceedings of the 10th International Conference on Bioinformatics and Bioengineering (BIBE 2010), pp.32-37 (2010) (Acceptance Rate 37%)
Press Release
[Job Experience]
Researcher, RIKEN Center for Advanced Intelligence Project (RIKEN AIP)
Senior Researcher, National Institute of Information and Communications Technology; NICT
Assistant Professor, The University of Tokyo
Special Postdoctoral Researcher (SPDR), Advanced Center for Computing and Communication, RIKEN