RIKEN Center for Advanced Intelligence Project AI Security and Privacy Team
Team Leader: Jun Sakuma (D.Eng.)
Along with the development of artificial intelligence (AI) technologies, decision making by machine learning is being widely implemented in society. In order for artificial intelligence to play a prominent role in decision making of humans, it is necessary to guarantee that private or confidential information is not leaked through the process of decision making by AI. Also, we need to guarantee that the behavior of AI is not manipulated by malicious attackers. Our team aims to develop fundamental technologies of security and privacy that are necessary for proper use of AI in society.
Main Research Fields
- Computer Science
Related Research Fields
- Artificial Intelligence Security
- Privacy Preservation in Artificial Intelligence
Papers with an asterisk(*) are based on research conducted outside of RIKEN.
- 1.Wen-Jie Lu, Shohei Kawasaki, and Jun Sakuma.:
"Using Fully Homomorphic Encryption for Statistical Analysis of Categorical, Ordinal and Numerical Data"
Network and Distributed System Security Symposium (NDSS) 2017 (to appear).
- 2.*Hiroaki Kikuchi, Takayasu Yamaguchi, Koki Hamada, Yuji Yamaoka, Hidenobu Oguri, and Jun Sakuma.:
"Ice and Fire: Quantifying the Risk of Re-identification and Utility in Data Anonymization"
The 30th IEEE International Conference on Advanced Information Networking and Applications (AINA) 2016, pp. 1035-1042 (2016).
- 3.*Rina Okada, Kazuto Fukuchi, and Jun Sakuma.:
"Differentially Private Analysis of Outliers"
European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML/PKDD) 2015, vol. 2, pp. 458-473 (2015).
- 4.*Kazuto Fukuchi and Jun Sakuma.:
"Neutralized Empirical Risk Minimization with Generalization Neutrality Bound"
European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML/PKDD) 2014, Vol. 1, pp. 418-433 (2014).
- 5.*Hirohito Sasakawa, Hiroki Harada, David duVerle, Hiroki Arimura, Koji Tsuda, and Jun Sakuma.:
"Oblivious Evaluation of Non-deterministic Finite Automata with Application to Privacy-Preserving Virus Genome Detection"
The 13th Workshop on Privacy in the Electronic Society (WPES) 2014, pp. 21-30 (2014).
- 6.*Hiroaki Kikuchi and Jun Sakuma.:
"Bloom Filter Bootstrap: Privacy-Preserving Estimation of the Size of an Intersection"
The 27th Annual IFIP WG 11.3 Working Conference on Data and Applications Security and Privacy (DBSec) 2013, pp. 145-163 (2013).
- 7.*Kazuto Fukuchi, Jun Sakuma, and Toshihiro Kamishima.:
"Prediction with Model-Based Neutrality"
European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML/PKDD), Vol. 2, pp. 499-514 (2013).
- 8.*Jun Sakuma, Hiromi Arai.:
"Online Prediction with Privacy"
The 27th International Conference on Machine Learning International Conference on Machine Learning (ICML) 2010, pp. 935-942 (2010).
- 9.*Jun Sakuma and Shigenobu Kobayashi.:
"Large-scale k-means clustering with user-centric privacy-preservation"
Knowl. Inf. Syst. Vol. 25, No. 2, pp. 253-279 (2010).
- 10.*Jun Sakuma and Shigenobu Kobayashi.:
"Link analysis for private weighted graphs"
The 32nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) 2009, pp. 235-242 (2009).
- Jun Sakuma
- Team Leader
1-1-1, Tennohdai, Tsukuba, IbarakiEmail: jun [at] cs.tsukuba.ac.jp