Rchr
J-GLOBAL ID：200901012830324425   Update date: Aug. 20, 2024

Sakuma Jun

サクマ ジュン | Sakuma Jun
Affiliation and department：
University of Tsukuba Faculty of Engineering, Information and Systems

About University of Tsukuba Faculty of Engineering, Information and Systems


Job title： Professor
Research field  (1)： Intelligent informatics
Research theme for competitive and other funds  (17)：
  • 2023 - 2028 Understanding Attack Mechanisms against AI through Causal Structures of Classification and Building Countermeasures
  • 2022 - 2027 分散型ソーシャルグラフに向けた差分プライバシー技術
  • 2022 - 2025 Understanding the impact of adversarial inputs on autonomous driving systems and developing countermeasure technologies
  • 2019 - 2023 Deep learning security and privacy focused on human-machine recognition gap
  • 2018 - 2023 Study on anonymization algorithm and risk to be re-identified using open data competition
Show all
Papers (193)：
  • Liu, Jiayang, Zhang, Weiming, Fukuchi, Kazuto, Akimoto, Yohei, Sakuma, Jun. Unauthorized AI cannot Recognize Me: Reversible Adversarial Example. Pattern Recognition. 2023. 134
  • Yu, Zhe, Fukuchi, Kazuto, Akimoto, Yohei, Sakuma, Jun. Domain Generalization via Adversarially Learned Novel Domains. IEEE Access. 2022. 10. 101855-101868
  • Fukuchi, Kazuto, Yu, Chia-Mu, Sakuma, Jun. Locally Differentially Private Minimum Finding. IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS. 2022. E105D. 8. 1418-1430
  • 田邊, 拓実, 福地, 一斗, 佐久間, 淳, 秋本, 洋平. モデル化誤差に頑健な Max-Min Off-Policy Actor-Critic. 人工知能学会全国大会論文集. 2022
  • Tran, Thien Q, Fukuchi, Kazuto, Akimoto, Yohei, Sakuma, Jun. Unsupervised Causal Binary Concepts Discovery with VAE for Black-box Model Explanation. Proceedings of the AAAI Conference on Artificial Intelligence. 2022. 9614-9622
ｍore...
MISC (15)：
  • 西山大輝, 西山大輝, 福地一斗, 福地一斗, 秋本洋平, 秋本洋平, 佐久間淳, 佐久間淳. CAMRI Loss: Improving the Recall of Prescribed Classes without Sacrificing Accuracy. 人工知能学会全国大会論文集(Web). 2023. 37th
  • Minimax optimal estimator for additively decomposable scalar functionals of discrete distributions. 2016. 116. 300. 259-265
  • Proximal Average Accelerated Proximal Gradient Algorithm with Adaptive Restart. 2016. 116. 300. 65-71
  • HASEGAWA Satoshi, SAKUMA Jun. Pairwise Co-link Propagation Kernel. 2013. 113. 139. 59-66
  • 菊池浩明, 佐久間,淳. Bloom Filter Bootstrapping: Privacy-Preserving Estimation of the Size of an Intersection. 27th Annual IFIP WG 11.3 Working Conference on Data and Applications Security and Privacy (DBSec '13). 2013. 55. 3
ｍore...
Patents (4)：
  • Program, classification method and system
  • Selection of elements strongly related to a predetermined reference element
  • プログラム、分類方法およびシステム
  • 選択装置、選択方法、プログラム、及び記録媒体
Books (3)：
  • Traveling Salesman Problem, Theory and Applications
    Intech 2010
  • Handbook of Evolutionary Technology: Computation and Applications
    近代科学社 2010
  • 交叉オペレータによる高次元分布推定とその最適化・モデル推定への応用
    2003
Lectures and oral presentations  (53)：
  • モデル化誤差に頑健な Max-Min Off-Policy Actor-Critic
    (2022年度人工知能学会全国大会(第36回) 2022)
  • Unsupervised Causal Binary Concepts Discovery with VAE for Black-box Model Explanation
    (36th AAAI Conference on Artificial Intelligence 2022)
  • Adaptive Scenario Subset Selection for Minimax Black-Box Continuous Optimization
    (GECCO '21 2021)
  • Convergence Rate of the (1+1)-Evolution Strategy with Success-Based Step-Size Adaptation on Convex Quadratic Function
    (GECCO '21 2021)
  • Level Generation for Angry Birds with Sequential VAE and Latent Variable Evolution
    (GECCO '21 2021)
ｍore...
Work history (6)：
  • 2012/02 - 現在 National Institute of Informatics
  • 2009/10 - 2013/03 Japan Science and Technology Agency PRESTO researcher
  • 2009/04 - 2012/03 University of Tsukuba Graduate school of SIE associate professor
  • 2007/04 - 2009/03 Tokyo Institute of Technology Assistant professor
  • 2004/07 - 2007/03 Tokyo Institute of Technology Assistant professor
Show all
Committee career (2)：
  • 2016/04 - 現在 ISO SC27/WG5 (アイデンティティ管理とプライバシー技術) 専門委員会 専門委員会委員
  • 2009/04 - 2012/03 人工知能学会 編集委員
Awards (17)：
  • 2019/10 - コンピューターセキュリティシンポジウム CSS2019優秀論文賞
  • 2019/10 - コンピューターセキュリティシンポジウム CSS2019学生論文賞 ノンインタラクティブな秘密計算上でのセット極大マッチの列挙
  • 2018/10 - コンピューターセキュリティシンポジウム CSS2018 最優秀論文賞 実世界でも攻撃可能なAudio Adversarial Example
  • 2018/10 - CSS2018奨励賞 Towards Practical Secure Automatic Speech Recognition
  • 2017/10 - 情報処理学会コンピュータセキュリティシンポジウム研究会 CSS2017優秀論文賞
Show all
Association Membership(s) (2)：
The Institute of Electronics, Information and Communication Enineers (IEICE) ,  THE JAPANESE SOCIETY FOR ARTIFICIAL INTELLIGENCE
※ Researcher’s information displayed in J-GLOBAL is based on the information registered in researchmap. For details, see here.

Return to Previous Page

TOP

BOTTOM