Scholar
Jun Sakuma
Google Scholar ID: v5emswQAAAAJ
Institute of Science Tokyo (Tokyo Institute of Technology), School of Computing
Citations & Impact
Citations
3,985
H-index
26
i10-index
65
Publications
20
Co-authors
18
list available
Contact
Publications
Resume (English only)
Academic Achievements
- Published numerous papers, see Google Scholar and DBLP for a complete list. Leads or co-leads multiple significant research projects across various fields including AI security and privacy.
Research Experience
- Currently serves as PI of the Machine Learning and Dependable AI Lab at Science Tokyo and also as PI of the AI Security and Privacy Team at RIKEN Center for Advanced Intelligence Project (AIP). Involved in several key projects such as Red Teaming Framework for Large Language Model Misalignment (JST K-program, 2024-2029) and Robust Federated Foundation Models via Synthetic Data Generation (JST Nexus, 2025-2028).
Education
- Professor at Science Tokyo and U. Tsukuba, Team leader at RIKEN AIP. Specific details about degrees, schools, and advisors are not provided.
Background
- 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. Also, working with external research organizations on the application of explainable AI to the pathological diagnosis of malignant lymphomas, and attacks on and defense of AI-assisted automated driving systems.
Miscellany
- Supervises research of several postdocs, doctoral students, master's students, and undergraduate students.
