Tudor Cebere

@mihaimaruseac Congrats!!

Yesterday was my last day at Google. It was a bittersweet departure, leaving a team I really enjoyed working with. GOSST's mission is extremely important and I still believe in it.

AI agents face a critical security threat: Indirect Prompt Injection (IPI) attacks hijack agent behavior to steal credentials and cause financial loss. We built the first system-level defense for Computer-Use Agents that actually maintains utility! That is, don't change the model, change the system around it to guarantee control flow integrity! arxiv.org/pdf/2601.09923

Join Inria PreMeDICal in Montpellier for a 6-month internship working on the @opendp_org Library! 🇫🇷 💻 Combine theory + code 📈 Path to PhD/Eng roles 📩 Send your CV + start date More Details: researchers.lille.inria.fr/abellet/jobs/O…

@mihaimaruseac Thanks!!

@TCebere That's awesome! Congratulations!

Grateful to be named a 2025 Google PhD Fellow in privacy, safety, and security! I am excited to continue my research in differential privacy, auditing, and trustworthy AI.🎉🎉

@BCebere Thanks!! ❤️

@TCebere Congrats! Keep up the good work💪

New paper: Conformal prediction for long-tailed classification🐒 arxiv.org/abs/2507.06867 🧑‍🌾 (plant enthusiast): Help me identify plants! 🤖 (existing conformal algs): Do you want sets that never include rare plants or sets that contain 100s of labels? 🧑‍🌾: Uhh… neither? A🧵(1/n)

ICML's election for their board of directors has begun. I've thrown my hat in the ring. Please consider voting for Gautam Kamath. I have experience with the governance of TMLR, COLT, and ALT, and I think I've demonstrated myself as a consciencious and engaged community member.

@jxmnop 1 good paper and 1 LLM generated one? Great batch, enjoy!

i just reviewed five papers for NeurIPS and it was an awful experience: - first paper was clearly LLM-generated. it was too short, the references didn't work, had no experiments or theory at all, and a ton of obvious mistakes. the more i read the less it made sense - two were actually the same paper! someone wrote the same content twice and submitted two versions under different titles - one was mildly interesting, but used a strange dataset, which turned out to be private unreleased data collected entirely within their company. ergo it's completely unreproducible - one of them was pretty good

Learned a lot by working through this! Check out Sham's tweet summarizing our work and the full note

RAGs are extremely useful, and yet there isn't an opensource RAG system for wikipedia (or I couldn't find it). So I built WikiRAG, a simple open-source github + hugging repo✨ Spin up your own RAG server for wikipedia in a single line. 🚗💨

@KairouzPeter Congrats on the award, well deserved! 🎉🎉

I’m deeply honored to receive the 2025 James L. Massey Research & Teaching Award for Young Scholars from the IEEE Information Theory Society 🎉🎊 itsoc.org/honors/massey-…

@gavinrbrown1 @WisconsinCS Congrats!!

I'm excited to announce that I will join @WisconsinCS as an assistant professor this fall! Time to get to it.

Without its international students, Harvard is not Harvard. hrvd.me/IntStudents25t

My team is hiring a Research Engineer!! If you would like to work with me on agentic privacy, apply here in the next two weeks job-boards.greenhouse.io/deepmind/jobs/…

SAVE THE DATE for the 2025 OpenDP Community Meeting on September 19th in Dublin, Ireland! We are thrilled to co-locate with the Eyes-Off Data Summit (@Oblivious) and can't wait to share more information on the agenda in the coming weeks - stay tuned 👀 sites.harvard.edu/opendp/events/…

@niloofar_mire @CMU_EPP @LTIatCMU @AIatMeta @kamalikac Congrats!!

📣Thrilled to announce I’ll join Carnegie Mellon University (@CMU_EPP & @LTIatCMU) as an Assistant Professor starting Fall 2026! Until then, I’ll be a Research Scientist at @AIatMeta FAIR in SF, working with @kamalikac’s amazing team on privacy, security, and reasoning in LLMs!

Excited to be in Singapore for ICLR, presenting our work on privacy auditing (w/ Aurélien & @NicolasPapernot). If you are interested in differential privacy/privacy auditing/security for ML, drop by (#497 26 Apr 10-12:30 pm) or let's grab a coffee! ☕ openreview.net/forum?id=xzKFn…

@CSProfKGD I am not a computer vision person, but I took his course during my masters. Unmatched passion for the field and a incredible teacher/human!

A prime example of the value of open, (ERC funded) academic research.

@matthieu_meeus @satml_conf @_igorshilov @yvesalexandre @MarekRei @shubhamjain0594 @ManuelFaysse Congrats to the authors, well deserved!

And we were lucky enough to win the @satml_conf best paper award!!🌟 @_igorshilov @yvesalexandre @MarekRei @shubhamjain0594 @ManuelFaysse