🔥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

Makes you wonder what kind of evidence they have, and got me thinking about this Neurips paper: arxiv.org/pdf/2402.14904. Any chance it's radioactive watermarking Tom Sander @ICLR Pierre Fernandez?

Glad to see our work on the privacy of synthetic data references in the International AI Safety Report! Paper: arxiv.org/abs/2306.10308 Work done with Matthieu Meeus, Florent Guépin, and Ana-Maria Cretu at Imperial College London.

Cool to see our work on developing ChocoLlama --a Flemish LLM-- be covered by newspaper De Tijd De Tijd 🍫 The article is only available in Dutch but that nicely fits the story. 📄Paper: arxiv.org/pdf/2412.07633 🧠Models: huggingface.co/ChocoLlama

Lovely inventive attack surface

And we were lucky enough to win the SaTML Conference best paper award!!🌟 Igor Shilov Yves-A. de Montjoye Marek Rei Shubham Jain Manuel Faysse

Can't wait to see everyone at ICLR and NAACL! Check out some of our awesome papers. Come and say hi, we'd love to have a chat :)

Yes yes I know the fundamental law of information recovery and differential privacy, but if there are really just a few summary statistics, surely it should be anonymous? 🥸 I definitely used to think this, until we started looking into it two years ago. A thread 🧵

🚨One (more!) fully-funded PhD position in our group at Imperial College London – Privacy & Machine Learning 🔐🤖 starting Oct 2025 Plz RT 🔄

!!!

Google presents Strong Membership Inference Attacks on Massive Datasets and (Moderately) Large Language Models