LAB LOGA page on LabLog, a review site (not the lab's official page)
Yang Cao Lab
Machine-translated · View original
The lab studies the privacy and safety of AI from both theoretical and systems perspectives.
AboutAbout the lab
Supporting trustworthy AI.
The Yang Cao Lab studies privacy protection and security technologies for using AI safely.
Focusing on large language models, autonomous agents, federated learning, and data infrastructure, the lab investigates what the dangers are and how to protect against them.
The lab builds theoretical foundations such as differential privacy and secure computation, and goes on to develop algorithms and systems that actually work.
In an international environment where Japanese and English are both spoken, the lab pursues research with the goal of presenting at international conferences.
Key terms
- Differential privacy
- A technique that adds a controlled amount of noise so that individuals cannot be identified, while preserving overall trends in the data
- Large language model
- An AI that learns how words connect from large amounts of text, and can generate text and respond
- Federated learning
- A way of building a model without pooling data, by collecting only the results of training done locally
NewsLab news
Paper accepted to the international conference ICML 2026
Paper accepted to the international conference ICLR 2026
Papers accepted to SIGMOD, VLDB, and AAAI 2026
Outstanding Paper Award at ACM MM 2025
ResearchResearch themes
The lab tackles the question of how AI and data science can be used in society in a safe and trustworthy way. Its research proceeds in three stages: building theoretical foundations, designing algorithms, and deploying them in real systems.
*Illustrative imageFoundations of Privacy Technology
The lab builds theoretical and algorithmic foundations for differential privacy, secure computation, TEEs (trusted execution environments), federated learning, and removing data from trained models (machine unlearning). It covers everything from rigorous guarantees to systems that can actually be run.
*Illustrative imageAttacks on and Defenses of AI
The lab studies how large language models and autonomous agents can be attacked and how they can be defended. It targets risks such as jailbreaking, prompt injection, and backdoor attacks.
*Illustrative imageTrustworthy Data Infrastructure
The lab designs data flows and AI systems that can be verified after the fact and that run reliably. Its work includes secure vector databases, data marketplaces, and safety evaluation that uses multiple types of data.
MembersFaculty
The members of the Yang Cao Lab are faculty, researchers, PhD, master's, and undergraduate students, international students, and secretaries.As of 2026
- Associate ProfessorYang Yang CaoPublications ↗
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 Yang Cao Lab
Kurihara LabSchool of Computing, Department of Computer ScienceSecurity and privacy technologies, anonymous communication
Takashi Ishida LabSchool of Computing, Department of Computer ScienceData mining and bioinformatics (advancing life sciences thro…
Heming Sun LabSchool of Computing, Department of Computer ScienceVideo compression, generative AI models, FPGA/ASIC co-optimi…
Haruhiko Kaneko LabSchool of Computing, Department of Computer ScienceError control codes and data compression technologies (highl…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: “Cybersecurity” jaydeep_ / CC0 (cropped)
- Foundations of Privacy Technology: “Solex 99 30 padlock with keys (DSCF2659)” Trougnouf / CC BY 4.0 (cropped)
- Attacks on and Defenses of AI: “NSOC-2012” Unknown photographer / Public domain (cropped)
- Trustworthy Data Infrastructure: “Network cables in server room” ProjectManhattan / CC BY-SA 3.0 (cropped)
- Related lab (栗原研究室): “EthernetSwitch” Raysonho / CC0 (cropped)
- Related lab (石田研究室): “4xhe pinnatoxin pentamer” Opabinia regalis / CC BY-SA 4.0 (cropped)
- Related lab (孫研究室): “Red-Square-sub-pixel-weirdness” librsvg2.40, Lommes / CC0 (cropped)
- Related lab (金子研究室): “Hard disk head crash” Alchemist-hp / CC BY-SA 3.0 (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.