1. Home
  2. Research
  3. Centers & Labs
  4. RIKEN Center for Advanced Intelligence Project
  5. Artificial Intelligence in Society Research Group

RIKEN Center for Advanced Intelligence Project AI Security and Privacy Team

Team Leader: Jun Sakuma (D.Eng.)

Research Summary

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 guarantee that that AI's behavior cannot be arbitrarily manipulated by a malicious attacker and AI cannot harm humans against the original AI designers’ intent. Our team aims to develop fundamental technologies of security and privacy that are necessary for proper use of AI in society.

Research Subjects:

  • Artificial Intelligence Security
  • Privacy Preservation in Artificial Intelligence

Main Research Fields

  • Informatics

Related Research Fields

  • Engineering
  • Humanities
  • Intelligent informatics
  • Information security

Keywords

  • machine learning
  • security
  • privacy
  • fairness

Selected Publications

  • 1. Thien Q. Tran, Kazuto Fukuchi, Youhei Akimoto, Jun Sakuma:
    "Statistically Significant Pattern Mining with Ordinal Utility."
    KDD 2020: pp. 1645-1655 (2020).
  • 2. Hiromu Yakura, Youhei Akimoto, Jun Sakuma.:
    "Generate (Non-Software) Bugs to Fool Classifiers"
    AAAI 2020: pp. 1070-1078 (2020).
  • 3. Hiromu Yakura, Shinnosuke Shinozaki, Reon Nishimura, Yoshihiro Oyama, Jun Sakuma.:
    "Neural malware analysis with attention mechanism"
    Comput. Secur. 87, 15 pages, (2019).
  • 4. Ryota Namba, Jun Sakuma.:
    "Robust Watermarking of Neural Network with Exponential Weighting"
    AsiaCCS 2019: pp. 228-240 (2019).
  • 5. Hiromu Yakura, Jun Sakuma.:
    "Robust Audio Adversarial Example for a Physical Attack"
    IJCAI 2019: pp. 5334-5341 (2019).
  • 6. Thien Q. Tran, Jun Sakuma.:
    "Seasonal-adjustment Based Feature Selection Method for Predicting Epidemic with Large-scale Search Engine Logs"
    KDD 2019: pp. 2857-2866 (2019).
  • 7. Toshihiro Kamishima, Shotaro Akaho, Hideki Asoh, Jun Sakuma.:
    "Model-based and actual independence for fairness-aware classification"
    Data Min. Knowl. Discov. 32(1): pp. 258-286 (2018).
  • 8. Takao Murakami, Hideitsu Hino, Jun Sakuma.:
    "Toward Distribution Estimation under Local Differential Privacy with Small Samples"
    PoPETs 2018(3): pp. 84-104 (2018).
  • 9. Kazuya Kakizaki, Kazuto Fukuchi, Jun Sakuma.:
    "Differentially Private Chi-squared Test by Unit Circle Mechanism"
    ICML 2017: pp. 1761-1770 (2017).
  • 10. Wenjie Lu, Shohei Kawasaki, Jun Sakuma.:
    "Using Fully Homomorphic Encryption for Statistical Analysis of Categorical, Ordinal and Numerical Data"
    NDSS 2017, 15 pages (2017).

Related Links

Lab Members

Principal investigator

Jun Sakuma
Team Leader

Core members

Jiayang Liu
Postdoctoral Researcher

Contact Information

SB1006
1-1-1, Tennohdai, Tsukuba, Ibaraki
Email: jun [at] cs.tsukuba.ac.jp

Top