This is a new laboratory established in April 2023. We study theory and methodologies of machine learning and dependable artificial intelligence, especially AI security and privacy, explainable AI, and AI fairness. Also, we are working with external universities on AI-based pathological diagnosis of malignant lymphoma, AI-based attacks on automated driving systems and security.
The PI of this lab (Sakuma) is also the PI of the AI Security and Privacy Team, RIKEN Center for Advanced Intelligence Project (AIP).
Research
Please refer to google scholar and DBLP for publication outputs. Recent research interests include:
AI security (attacks on AI, adversarial examples, model poisoning, model inversion), AI privacy (differential privacy, multiparty computation), explainable AI, AI fairness, copyright protection of AI models and AI-generated knowledge, and language model security and privacy.
Real-world application problems working with outside research organizations includes the application of explainable AI to the pathological diagnosis of malignant lymphomas, and attacks on and defense of AI-assisted automated driving systems.
Major projects (as of Sept. 2025)
Red Teaming Framework for Large Language Model Misalignment (JST K-program, Principal Investigator, 2024-2029)
Robust Federated Foundation Models via Synthetic Data Generation (JST Nexus, Principal Investigator, 2025-2028)
Understanding Attack Mechanisms against AI Considering Causal Structure in Discrimination and Building Defense Strategies (Grant-in-aid for scientific research, Fundamental Research A, PI, FY2023-2027)
Static and dynamic reliability assurance of AI-driven hypotheses and their application in medicine (JST CREST, co-PI, FY2021-2026)
Differential privacy for distributed social graphs (Grant-in-aid for scientific research, Fundamental Research A, co-PI, FY2022-2026)
Members (As of Sept. 2025)
PI Jun Sakuma (Professor, Science Tokyo and U. Tsukuba, Team leader, RIKEN AIP)
Assistant Prof. Rui Wen (Science Tokyo)
Cooperating Faculties Yohei Akimoto (Assoc. Prof, U. Tsukuba), Kazuto Fukuchi (Assist. Prof, U. Tsukuba)
Post Docs YU ZHE (RIKEN AIP/Science Tokyo), SUN LU (RIKEN AIP/Science Tokyo), Liu Jiayang (Science Tokyo)
Doctoral Students Daiki Nishiyama (D3, Science Tokyo), Yixin TAN (D2, Science Tokyo), Jiaen Liu (D1, Science Tokyo)
Master Students Kenta Tsuji(M2/Science Tokyo), Kazuki Fujii(M2/Science Tokyo), Shojiro Yamabe(M2/Science Tokyo) , Chai Jianzhe (M2/Science Tokyo), Students Souta Ogawa(M1/Science Tokyo) , Kosuke Fujita (M1/Science Tokyo), Jiayang Yang (M1/Science Tokyo), Tin-Wei Liao (M1/Science Tokyo)
Undergrad, Kenta Kawamoto (B4/Science Tokyo), Takato Ui (B4/Science Tokyo)
Research Associate Takaaki Toda (RIKEN AIP/ Waseda U. M2), Shiwen AN (RIKEN AIP/Science Tokyo D1), Nihal Md Ragib Amin (RIKEN AIP/Science Tokyo D2), WEI JUNHAO(RIKEN AIP/Science Tokyo D2), Mikoto Kudo (RIKEN AIP/U. Tsukuba, D2), Gong Nanxin (RIKEN AIP/Science Tokyo D3),
Internship student/ International exchange student
Magnus Lim (Nanyang Technological University)
Alumni
Yu-Lin Tsai (RIKEN AIP/National Yang Ming Chiao Tung University)
Ziling He (RIKEN AIP/Waseda U.)
Wong Ji Kean (National University of Singapore/ Tokyo Tech.) 2025.3
Yusuke Hayashi (B4/Tokyo Tech.) 2025.3
Kazuya Kakizaki (D3, U. Tsukuba) 2025.3
Joshua Butke (RIKEN AIP/Tokyo Tech.)
Ting-Wei Liao (RIKEN AIP/National Yang Ming Chiao Tung University)
Pengfei Liu (Harbin Institute of Technology)
Khaled N. Khasawneh (Visiting scholar, George Maison University) 2024.5
Win Lei Thwe(Research student, U. Tsukuba) 2024.3
Takaki Kato (B4, U. Tsukuba) 2024.3
Yuto Yoshinari (B4, Tokyo Tech. ) 2024.3
XU KAIWEN (M2, U. Tsukuba) 2024.3
Mitsuhiro Fujikawa (M2, U. Tsukuba) 2024.3
Rei Nagaike (M2, U. Tsukuba) 2024.3
Dai Shengtian (M2, U. Tsukuba) 2024.3
Ryoma Senda (RIKEN AIP/Tokyo Tech) 2024.3
Masahiro Fujisawa(RIKEN AIP/Tokyo Tech) 2023.10
Access:
152-8550 2-12-1, Ookayama, Meguro, Tokyo, Japan
Ookayama campus, West #8 bldg. E-905
Our lab is located on the 9th floor, and the entrance is locked.
Please call Mitsudera (三寺) san to open the gate.
The phone number of Mitsudera san is shown at the gate.