Tight Auditing of Differential Privacy in MST and AIM Georgi Ganev, Meenatchi Sundaram Muthu Selva Annamalai, Bogdan Kulynych http://arxiv.org/abs/2604.18352

👋 We have two fully-funded PhD positions open at @hpi.bsky.social with the Chair of Human-Centered Transformative AI. 1) On efficient transformer architectures with a focus on recurrent approaches jobs.plattnerfoundation.org/HPI/job/Pots... 1/2

A Gaussian mechanism with ε = 6 can be less private than one with ε = 8. This points to a problem with how we report privacy guarantees in machine learning. A thread 🧵

Thrilled to present our paper "Unintended Memorization of Sensitive Information in Fine-Tuned Language Models" at #EACL2026 in Rabat! 🇲🇦 w/ J. Marin Ruiz, G. Kaissis, P. Seidl, R. v. Eisenhart-Rothe, F. Hinterwimmer & @danielrueckert.bsky.social. Read here: arxiv.org/abs/2601.174...

Optimal conversion from Rényi Differential Privacy to $f$-Differential Privacy Anneliese Riess, Juan Felipe Gomez, Flavio du Pin Calmon, Julia Anne Schnabel, Georgios Kaissis http://arxiv.org/abs/2602.04562

We extracted (parts of) 12 books in experiments with 4 frontier-lab, production LLMs. We prompted the LLMs with a short prefix of a book and asked them to complete the rest. For Harry Potter and the Sorcerer’s Stone, we extracted 95.8% of the book from jailbroken Claude 3.7 Sonnet.

Let’s today not only commemorate Rosalind Franklin, but also Raymond Gosling, her @kingscollegelondon.bsky.social postgraduate who took photo 51…

I am overjoyed to announce that I have joined HPI as a full professor for Human-Centred Transformative AI. I am looking forward to working with my amazing new and current collaborators and would like to deeply thank everyone who has been part of the journey that led me here! @hpi.bsky.social

Zum 1. November trat Prof. Dr. med. Georg Kaissis seine Professur für #DigitalHealth: Human-Centred Transformative AI an. Sein Forschungsschwerpunkt: die Entwicklung der nächsten Generation multimodaler #KI-Modelle. Mehr Infos zur neuen Professur: hpi.de/artikel/prof...

We celebrated the 5th anniversary of our research chair at @tum.de! 💙🥂 It's been an incredible journey of research and collaboration. Thank you to everyone who has made this possible. We are very much looking forward to the next years to come! #AIMAnniversary #AIMNews

VaultGemma: A Differentially Private Gemma Model Amer Sinha, Thomas Mesnard, Ryan McKenna, Daogao Liu, Christopher A. Choquette-Choo, Yangsibo Huang, Da Yu, George Kaissis, Zachary Charles, Ruibo Liu, Lynn Chua, Pritish Kamath, Pasin Manurangsi, Steve He, Chiyuan ... http://arxiv.org/abs/2510.15001

It has been a privilege to work with so many amazing colleagues across Google and Google DeepMind to build VaultGemma, an LLM trained from scratch with Differential Privacy. Weights are openly available! Check it out here: research.google/blog/vaultge...

Due to physical resource constraints, we currently estimate that around 300–400 of the candidate papers recommended for acceptance by the ACs will need to be rejected. We seek the support of our 41 SACs in addressing this distributed optimization problem in a fair and professional manner.

NeurIPS has decided to do what ICLR did: As a SAC I received the message 👇 This is wrong! If the review process cannot handle so many papers, the conference needs yo split instead of arbitrarily rejecting 400 papers.

📣 Researchers in AI security, privacy & fairness: It's time to share your latest work! The SaTML 2026 submission site is live 👉 hotcrp.satml.org 🗓️ Deadline: Sept 24, 2025 @satml.org

NeurIPS is endorsing EurIPS, an independently-organized meeting which will offer researchers an opportunity to additionally present NeurIPS work in Europe concurrently with NeurIPS. Read more in our blog post and on the EurIPS website: blog.neurips.cc/2025/07/16/n... eurips.cc

New preprint on the most precise as of yet mapping between differential privacy and common operational notions of privacy risk used in practice:

The Hitchhiker's Guide to Efficient, End-to-End, and Tight DP Auditing Meenatchi Sundaram Muthu Selva Annamalai, Borja Balle, Jamie Hayes, Georgios Kaissis, Emiliano De Cristofaro http://arxiv.org/abs/2506.16666

Responsible medical AI demands patient-level privacy. Our recent #TPDP '25 paper extends Differential Privacy #DP beyond individual data points to protect entire patient profiles. 🧠 📄 Read the paper: tinyurl.com/k9fz456a 🎥 Watch the video: tinyurl.com/2jx528m5

Going to be at CVPR the next couple of days presenting our paper „A Tale of Two Classes: Adapting Supervised Contrastive Learning to Binary Imbalanced Datasets“. arxiv.org/abs/2503.17024 Always happy to meet anyone working on representation learning or tabular DL and medical data

Markiert es euch im Kalender: Die IOI 2027 kommt ans HPI! 🎉 Zum ersten Mal seit 1992 kommt die Internationale Informatik-Olympiade (IOI) zurück nach Deutschland und wir sind in Kooperation mit Bundesweite Informatikwettbewerbe (BWINF) stolze Gastgeber des renommierten Wettbewerbs.

Check out our new pre-print "Strong Membership Inference Attacks on Massive Datasets and (Moderately) Large Language Models", joint work with fantastic colleagues from Google (DeepMind) and many other great institutions! Find it here: arxiv.org/abs/2505.18773

Check out our new pre-print "Redirection for Erasing Memory (REM): Towards a universal unlearning method for corrupted data", joint work with excellent colleagues from Google DeepMind, Google Research and University of Cambridge. Check it out here! arxiv.org/abs/2505.17730

We are incredibly proud of Prof @danielrueckert.bsky.social for being elected as Fellow of the Royal Society! Well deserved and a testament to your dedication to research 🎉

Now, it's time to up the ante. We are committed to enshrining scientific freedom in EU law, creating a 7-year ‘super grant’ to attract top researchers, and expanding support for the most promising scientists. More → europa.eu/!TTbWbJ

Data attribution is crucial for debugging models and detecting low quality data (spotting mislabeled samples, bias etc.). But many methods aren't mathematically sound and don’t scale. But how could we improve this for large models? 1/n

Excited to share: “A Tale of Two Classes: Adapting Supervised Contrastive Learning to Binary Imbalanced Datasets” has been accepted to #CVPR2025! 🎉 Paper: lnkd.in/esKRqF5p Code: lnkd.in/eZFvDA5Q (Thread incoming 👇)

Would you present your next NeurIPS paper in Europe instead of traveling to San Diego (US) if this was an option? Søren Hauberg (DTU) and I would love to hear the answer through this poll: (1/6)

Congratulations to my revered mentor and dear friend @danielrueckert.bsky.social for this great honour and for the outstanding and enduring achievements that underlie it!

$( varepsilon, δ)$ Considered Harmful: Best Practices for Reporting Differential Privacy Guarantees Juan Felipe Gomez, Bogdan Kulynych, Georgios Kaissis, Jamie Hayes, Borja Balle, Antti Honkela http://arxiv.org/abs/2503.10945

#FUTURE-AI: International Experts Define Guidelines for Trustworthy Healthcare AI 📝 👉Learn more: t1p.de/2rgfh 👉Check out the interview with Prof. Julia Schnabel & Dr. Georgios Kaissis: t1p.de/e9g6a #TrustworthyAI

Huge congratulations to our two PhD students, Tamara Müller and @zilleralex.bsky.social , on completing their doctoral journeys! Your hard work and dedication have paid off. Wishing you both all the best for your future endeavors!

#WACV2025 just wrapped up and our group was also present, with a novel framework for improving image-to-graph transformation! Have a look at how Alex Berger et al. enable cross-domain & cross-dimension learning to outperform standard transfer learning on vessel graph extraction! 🚀 shorturl.at/v6SJi

🎙️Interview with Prof Julia Schnabel, #HelmholtzMunich: FUTURE-AI – Making #AI in Healthcare Trustworthy by Design 👉 Learn how FUTURE-AI is paving the way for transparent & deployable medical AI tools: t1p.de/e9g6a @ja-schnabel.bsky.social @helmholtzai.bsky.social @www.helmholtz.de #TrustworthyAI

European alternatives for digital services. Sovereignty matters.

Registration for CSLaw 2025 is now open! Please share far and wide! Early bird prices are available until February 24. The main conference will begin March 25! Register here: web.cvent.com/event/dbf97d...

I unceremoniously departed from Twitter/X and I'm here now 😀.