AKIRA TANAKA

Cybersecurity Research Institute
Center for Research on AI Security and Technology Evolution

Akira Tanaka received his Ph.D. in Mathematics from Kyushu University in 2022. During his master's and doctoral studies, he applied machine learning (ML) to industrial problems, including GPS navigation, evacuation planning, and more. His research was not only accepted at top-tier conferences but also resulted in patents and was implemented as real-world services.

Since 2021, he has been a researcher at the National Institute of Information and Communications Technology (NICT), focusing on ML applications in cybersecurity, particularly darknet analysis. From 2025 onward, his main research interest has been securing AI/ML models, especially large language models (LLMs).

Research interests: safety alignment, botnet tracking, mechanistic interpretability, static malware analysis
Keyword: AIxCybersecurity, AI security, AI for cybersecurity, darknet, malware analysis

Selected papers

Akira Tanaka, et al. "Offline map matching using time-expanded graph for low-frequency data", Transportation Research Part C: Emerging Technologies, Volume 130, September 2021, DOI: 10.1016/j.trc.2021.103265. (Top-tier journal)
Akira Tanaka et al. "Proposing a Genetic Algorithm Approach for Unveiling Fingerprint of Internet-Wide Scanner,” Proceedings of the Computer Security Symposium 2021 (CSS2021), Japan, October 2021 (Student Paper Award in Japanese domestic conference).
Akira Tanaka, Chansu Han and Takeshi Takahashi, “Detecting Coordinated Internet-Wide Scanning by TCP/IP Header　Fingerprint”, IEEE Access, vol. 11,pp. 23227-23244, 2023, doi: 10.1109/ACCESS.2023.3249474.
Akira Tanaka et al. “Practical Approach to Evacuation Planning Via Network Flow and Deep Learning,” BigGraphs 2017, in Boston, MA, USA, 2017.

Back to the members list

Cybersecurity Research InstituteClick here for other organizations

cybersecurity research institute top