Yves-A. de Montjoye
@yvesalexandre
Followers
5K
Following
3K
Statuses
2K
Associate Professor of Applied Math at @ImperialCollege. SpAd to @DReynders (🇪🇺). Member of @APD_GBA (🇧🇪 DPA). @MIT @MediaLab PhD. Opinions are my own.
London, England
Joined April 2008
🚨 New @icmlconf paper from our group on copyright traps. A method for content owners to detect whether their text was used to pre-train or fine-tune an LLM.
1/10 New paper alert! 🚨We investigate the use of copyright traps to detect if Large Language Models (LLMs) have been trained on specific content. More details in thread or find us at ICML 2024 @icmlconf in Vienna 🇦🇹 next week 🧵👇
0
1
9
Glad to see our work on the privacy of synthetic data references in the International AI Safety Report! Paper: Work done with @matthieu_meeus, Florent Guépin, and @AnaMariaCretu5 at @imperialcollege.
Today, we are publishing the first-ever International AI Safety Report, backed by 30 countries and the OECD, UN, and EU. It summarises the state of the science on AI capabilities and risks, and how to mitigate those risks. 🧵 Link to full Report: 1/16
0
2
8
This is joint work with fantastic colleagues from @EPL_UCLouvain: @cynddl (now at @oiioxford) and Julien Hendrickx. The paper is available at
0
0
0
RT @ImperialDSI: Associate Professor @yvesalexandre said: “Our new scaling law provides, for the first time, a principled mathematical mode…
0
1
0
RT @ImperialDSI: 💻⚠️NEW! Computer scientists from @imperialcollege's DSI, @oiioxford and Université catholique de Louvain have developed a…
0
4
0
Join us at Imperial College for an exciting event on the future of privacy in machine learning! 🔒🤖The application for lightning talks is open. 🗓️Date: Feb 4 @ 6pm 📍Imperial College London
We're very excited to host this meetup and we'd be thrilled to see you there! And a huge shoutout to my co-organizers @matthieu_meeus, Nataša Krčo (not on twitter), @yvesalexandre and @ImperialDSI team!
0
2
8
The FT said this is where the cool kids hang out. So, here I am, trying to be cool. 🐑👴
"This is really getting quite remarkable • BlueSky user numbers have doubled in the past week and now total 3.5 million across US & UK 🚀 • Number of people deleting their X/Twitter account remains way up And the next chart is particularly notable... • Despite a massive head start, BlueSky has now overtaken Threads in the US 👇" — @jburnmurdoch
0
0
1
Great piece by Melissa on Nightshade, what it provides and what it doesn't do.
Meet @TheGlazeProject, the AI lab behind Glaze and Nightshade, two prominent weapons in an artist’s arsenal against nonconsensual AI scraping. The lab wants to tilt the balance of power from Big Tech back to individual creators. But are their tools enough?
0
0
2
RT @_igorshilov: ‼️Unfortunately, we are cancelling our Privacy/Machine Learning meetup scheduled for tomorrow‼️ While the planned tube st…
0
1
0
Short piece by @imperialcollege on our recent award 🏅at @acm_ccs for QueryCheetah 🐆, a tool for fast automated discovery of vulnerabilities in data APIs and query-based systems
0
2
9
Importantly, we believe in the importance of diversity in both our group and the research fields we work in. We thus encourage *people from all backgrounds*, including underrepresented communities, to contact us and apply:
0
0
0