Mohammad Sabokrou
Trustworthy Machine Learning

Trustworthy AI, Machine Learning, and Computer Vision

I am an Associate Professor at New Uzbekistan University and a Visiting Researcher at the Okinawa Institute of Science and Technology (OIST), Japan. My research focuses on trustworthy machine learning, anomaly detection, out-of-distribution detection, continual learning, and AI robustness. Previously, I led AI research initiatives at the Institute for Research in Fundamental Sciences (IPM) in Tehran, Iran, and worked as a Senior Researcher in Finland and France, including at the Center for Machine Vision and Signal Analysis (CMVS). My work bridges machine learning foundations and practical robustness for reliable, secure, and effective AI systems.

View Publications Collaborate With Me
New Uzbekistan University campus in Tashkent
New Uzbekistan University Associate Professor · Tashkent, Uzbekistan
OIST campus in Okinawa, Japan
Okinawa Institute of Science and Technology (OIST) Visiting Researcher · Okinawa, Japan
Campus photos: New Uzbekistan University · OIST / CC BY 2.0

Research Vision

I develop AI systems that remain dependable beyond controlled benchmarks—when data shift, unknown categories appear, inputs are corrupted or adversarial, and models must continue learning. My work connects anomaly and out-of-distribution detection, robustness, continual learning, and AI security to move trustworthy machine learning from accuracy alone toward reliable behavior in the real world.

Research Interests

  • Trustworthy machine learning
  • Anomaly detection & out-of-distribution detection
  • Continual and lifelong learning
  • Robustness, safety, and reliability in AI

Join the Group

I welcome motivated people interested in trustworthy machine learning, anomaly detection, AI safety, and robust computer vision.

Research collaboratorsResearch assistantsInternsPostdoctoral researchersVisiting researchers

Current opportunities: funded and volunteer research-assistant or internship opportunities may be available depending on the project and host institution.

To apply, please include:

  • Your CV
  • A short description of your research interests and relevant skills
  • Selected publications, code, or project links, if available
  • The role and preferred starting period
Apply or propose a collaboration

Research Impact

2Active JSPS KAKENHI projects as Principal Investigator
5Area Chair appointments listed for ICLR, NeurIPS, and BMVC
4Core research themes spanning trustworthy and adaptive AI
GlobalResearch collaborations across Asia, Europe, and North America

For current citation and h-index information, see Google Scholar.

Selected Research Projects

  • Investigating the Trustworthiness of Deep Pre-trained and Self-Supervised Models
    2024–2028 · ¥4,680,000 · Principal Investigator
    Japanese national research funding: JSPS KAKENHI, Grant-in-Aid for Early-Career Scientists · Funded at the Okinawa Institute of Science and Technology (OIST), Okinawa, Japan · Official JSPS KAKENHI program
  • Breaking Boundaries: Robust, Domain-General Anomaly Detection with Vision-Language Models
    2026–2030 · ¥18,330,000 · Principal Investigator
    Japanese national research funding: JSPS KAKENHI, Grant-in-Aid for Scientific Research (B) · Funded at the Okinawa Institute of Science and Technology (OIST), Okinawa, Japan · Official KAKEN record (26K02988)
  • AI Safety and Security for Classical AI Models
    Institute for Research in Fundamental Sciences (IPM)

Selected News

  • 13 August 2026: I will serve as an Area Chair for ICLR 2027.
  • 9 August 2026: Paper accepted at BMVC 2026, the British Machine Vision Conference, on robust and trustworthy computer vision / anomaly detection.
  • 8 August 2026: Joined New Uzbekistan University as an Associate Professor.
  • Area Chair, NeurIPS 2026.
  • Awarded JSPS KAKENHI (Scientific Research B), 2026–2030.
  • Area Chair, BMVC 2026.
  • Two papers accepted at NeurIPS 2025.
  • Area Chair, ICLR 2026.
  • Paper accepted at ICLR 2025 on adversarially robust anomaly detection.
  • Paper accepted to TMLR on stealthy backdoor attacks via confidence-driven sampling.
  • Paper accepted at NeurIPS 2024 on scanning trojaned models using out-of-distribution samples.

Academic Service to the Community

Area Chair

Reviewer / Program Committee

Organization

Do You Need a Recommendation Letter?

If you would like to request a recommendation letter from me, please review the required information and submission guidelines before contacting me.

Recommendation Letter Guidelines