www.scientificamerican.com/article/hack...
New article by Deni Bechard at Scientific America covering our work on hijacking Multimodal computer agents published on Arxiv earlier this year. A massive effort by Lukas Aichberger, supported by myself Yarin Gal, Philip Torr, FREng, FRS & Adel Bibi
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
Excited to share our paper: "Chain-of-Thought Is Not Explainability"! We unpack a critical misconception in AI: models explaining their steps (CoT) aren't necessarily revealing their true reasoning. Spoiler: the transparency can be an illusion. (1/9) 🧵
Not every day you see a paper you worked on featured by a youtube channel you've watched before :) youtu.be/KY7_ufxh_Rk?...
Read more: cemde.github.io/Domain-Certi...
Thanks to my amazing collaborators:
- @alasdair-p.bsky.social, Preetham Arvind, @maximek3.bsky.social, Tom Rainforth, @philiptorr.bsky.social, @adelbibi.bsky.social at @ox.ac.uk
- Bernard Ghanem at KAUST
- Thomas Lukasiewicz at @tuwien.at.
(7/7)
⚠️ Beware: Your AI assistant could be hijacked just by encountering a malicious image online!
Our latest research exposes critical security risks in AI assistants. An attacker can hijack them by simply posting an image on social media and waiting for it to be captured. [1/6] 🧵
A few weeks ago in Davos, Demis Hassabis highlighted the need to develop a "CERN for AGI" to ensure that advances at frontier level remain safe. I totally agree with him: We need this kind of international cooperation. youtu.be/U7t02Q6zfdc?...
The amazing collaborators: Preetham Arvind, @alasdair-p.bsky.social, Maxime Kayser, Tom Rainforth, Thomas Lukasiewicz, Philip Torr, Adel Bibi.
A @oxfordtvg.bsky.social production.
(6/6)
Link to paper:
openreview.net/forum?id=brD...
