LAB LOGA page on LabLog, a review site (not the lab's official page)
System Dependability Lab
Machine-translated · View original
A lab that evaluates and improves the reliability of AI systems using probabilistic models.
AboutAbout the lab
Capturing the uncertainty of AI systems to make them dependable.
The System Dependability Lab studies technologies that capture uncertain factors in AI systems, such as errors, failures, and degradation, to realize more dependable and efficient AI systems.
Using probabilistic models, the lab quantitatively evaluates reliability and performance, and also works on design optimization while considering quality trade-offs.
Its research targets include systems that use machine learning, systems that use UAVs (unmanned aerial vehicles), and long-running software.
The lab's website presents it under the name "Dependable AI Systems Lab (DAIS)."
Key terms
- N-version programming
- An approach to developing dependable software. The lab applies it to configurations that use diverse machine learning models and data.
- Fog computing
- A approach that distributes computation across devices close to where data is generated, such as IoT sensors and smartphones.
- Software rejuvenation
- A preventive technique that restarts software to clear its degraded state. The degradation is called software aging.
NewsLab news
A paper by a doctoral student was accepted at MASCOTS 2026
A paper by a doctoral student was accepted for publication in Future Generation Computer Systems
A paper by a master's student was accepted at ISSRE 2026
A paper by a master's student was accepted at DSML2026, and a paper from joint research with Honda was accepted at CRAI2026
The lab developed a quality design method for real-time video surveillance systems using unmanned aerial vehicles (press release)
ResearchResearch themes
The lab captures the uncertain behavior of AI systems, quantitatively analyzes system reliability and availability, and aims for designs that optimize cost. It also works on quality design of dependable AI systems and UAV systems, and on automatic development of dependable software using large language models.
*Illustrative imageMaking AI systems more dependable
In systems that use machine learning, such as self-driving cars, incorrect outputs can lead to accidents. Applying the idea of N-version programming, the lab is studying configurations that improve reliability by using diverse machine learning models and data.
*Illustrative imageDependable automated software development with LLMs
Techniques that use large language models (LLMs) for program development and debugging are attracting attention. The lab is studying methods to improve the reliability of the code and fixes (patches) that LLMs generate.
*Illustrative imagePerformance and reliability analysis of fog computing
Fog computing allows its configuration and behavior to be changed flexibly, but guaranteeing the quality of performance and availability can become difficult. The lab models it with stochastic reward nets, aiming at quantitative analysis of performance and availability and at design optimization.
*Illustrative imageSoftware degradation analysis and preventive maintenance
In long-running software, software aging, in which performance and reliability degrade over time, may be observed. By statistically analyzing operational data and predicting trends and failures, it becomes possible to plan preventive maintenance such as software rejuvenation.
MembersFaculty
The members of the System Dependability Lab are professors and other faculty, doctoral, master's, and undergraduate students, visiting researchers, and international research students.As of 2026
- Associate ProfessorFumio Machida
VoicesStudent voices
Ratings and reviews reflect the experiences of individual current or former students, not the lab's official views. Whether a lab has reviews, or how many, says nothing about the lab itself.
Students who take part in an interview may receive a thank-you gift worth ¥1,000, regardless of what they say.
Student ratings (0 students)
--
--
--
--
--
--
Student voices answer questions like these
- What's great about this lab?
- What did you learn after joining?
- What's the vibe, and what is the professor like?
- Who is this lab for?
- Where do graduates go?
Your experience can help younger students choose their lab. Your name won't be shown.
Write a lab reviewAnonymous · Your draft is saved if you stopRelatedLabs similar to System Dependability Lab
Program Logic LabSchool of Informatics, College of Information ScienceSymbols for creating program reliability. Research on progra…
System Security LabSchool of Informatics, College of Information ScienceDeveloping technologies for the safe use of information syst…
Operating Systems and System Software LabSchool of Informatics, College of Information ScienceA laboratory creating foundational software: operating syste…
Black-Box Optimization LabSchool of Informatics, College of Information ScienceOptimization of complex systems; development of general-purp…The information on this page is compiled by the LabLog team from the lab's public information and interviews. For corrections or removal requests, please contact LabLog, not the lab.
Report an errorAbout the images
The top and research theme images are illustrative and were not taken at the lab. They are cropped from Wikimedia Commons images. Cropped CC BY-SA images are provided under the same CC BY-SA license as the original (version shown on each line).
- Top image: “Nec-cluster” Hindermath / CC BY-SA 3.0 (cropped)
- Making AI systems more dependable: “Zoox Toyota Highlander Test Vehicle - Sensor Closeup - San Francisco, May 2025 07” 9yz / CC BY 4.0 (cropped)
- Dependable automated software development with LLMs: “Programmer at work (Unsplash)” Crew crew / CC0 (cropped)
- Performance and reliability analysis of fog computing: “Distributed storage differences” Álvarosvb / CC0 (cropped)
- Software degradation analysis and preventive maintenance: “PDC server room” Esquilo / CC BY-SA 3.0 (cropped)
- Related lab (
プログラム論理研究室): “MIDI note player source code” Yadarwish / CC BY-SA 3.0 (cropped) - Related lab (システムセキュリティ研究室): “LC-P computer keyboard - IC encapsulated on printed circuit board-3464” Raimond Spekking / CC BY-SA 4.0 (cropped)
- Related lab (オペレーティングシステムと
システムソフトウェア研究室): “Bacloud.com data center 2” Fleshas / CC BY-SA 4.0 (cropped) - Related lab (ブラックボックス最適化研究室): “Server Room Terminals ( )” Jon Parise / CC BY-SA 2.0 (cropped)
About LabLog
LabLog is a lab review app for students only. Student members at each university interview students in labs and publish what they say. Student voices can only be read by students who sign up with a university email address. Operated by bestiee Inc.
Learn more about LabLog ↗Search engines and AI may reference the basic lab info and rating summaries on this page and the description of LabLog. Student voices are for student members only. Automated collection by programs (scraping, or input to or training of AI) is prohibited under Article 8 of the Terms of Service. If you need data for research or analysis, please contact us.