🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

On my way to the 37th Gesellschaft für Informatik e.V. Kryptotag (#crypto days) where I’ll be giving the keynote talk on #trustworthy #MachineLearning #ML! Looking forward to many exciting conversations 🎙️

This is a very cool tool! You should check that out! 🥳

This work was accepted at #NeurIPS24. Great work with Dominik Hintersdorf and Lukas Struppek!!

Check also the blogpost with a small summary of our main findings: sprintml.com/2024/12/10/ope…! #NeurIPS2024 #OpenLLMs #Privacy #DifferentialPrivacy

Check out our #NeurIPS2024 paper "Finding NeMo: Localizing Neurons Responsible For Memorization in Diffusion Models" ⏰ Wed 11 Dec | 4:30 pm 📍East Hall A-C #2808 🖥️ arxiv.org/abs/2406.02366 With Dominik Hintersdorf Kristian Kersting @fraboeni Adam Dziedzic Happy to have a chat 😃

Come to our poster #6205 at #NeurIPS2024 We’re presenting with Pratyush Maini the work with Nick Jia and Nicolas Papernot on LLM Dataset Inference: we are able to determine if a given dataset was used to train an LLM. We show that membership inference attacks did not work

We’re getting started in the East Hall #2204 talking about Open vs Closed #LLMs and their adaptations with #privacy. #NeurIPS2024 #private #tuning 🔒

Come and find us to learn about localizing #memorization in individual parameters of #SSL models. 📍East Hall, #3411, at #NeurIPS2024

Check out our latest work that has been recently accepted at ICLR'25 🥳.

Today @fraboeni and Adam Dziedzic kicked off the new semester with a full lecture hall. 👩‍🎓If you also want to learn about #Trustworthy #MachineLearning, we invite you to follow our lecture online: youtube.com/playlist?list=…! #teaching #university #students #semester

I‘m so excited. The 120 students who signed up definitely show that there is a need to learn about novel facets and risks of machine learning. We compiled all the content around trustworthy ML into one overview lecture with videos, reading lists, and coding assignments! 👩‍💻

I am excited to announce that I have been named "Distinguished Reviewer" for the #SaTML #conference, the second year in a row.

Super excited to announce the second batch of speakers for our DIG-BUG's workshop on #reliable and #trustworthy #GenerativeAI at #ICML’25! Looking forward to Tatsunori Hashimoto, Eric Wong and Ivan Evtimov! Hope to see all of you there.