iiinova — where your digital self keeps evolving

Reposted by Torr Vision Group Oxford

Alasdair Paren @alasdair-p.bsky.social · 04/09/2025

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

011

Reposted by Torr Vision Group Oxford

Fazl Barez @fbarez.bsky.social · 01/07/2025

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) 🧵

28531

Reposted by Torr Vision Group Oxford

Professor Philip Torr, Oxford University @philiptorr.bsky.social · 10/06/2025

Youtuber Sabine Hossenfelder has picked up on our paper on how to fool AI agents, you can watch her desrcibing our work here: www.youtube.com/watch?v=KY7_....

youtube.com

AI is becoming dangerous. Are we ready?

YouTube video by Sabine Hossenfelder

011

Reposted by Torr Vision Group Oxford

Professor Philip Torr, Oxford University @philiptorr.bsky.social · 03/04/2025

Excited to be working with the UK Excited to be work with the UK AI Security Institute, even more important than normal in these turbulent times. www.linkedin.com/posts/philip...

linkedin.com

Strengthening AI Resilience | AISI Work | Philip Torr

Excited to be work with the UK AI Security Institute, even more important than normal in these turbulent times.

021

Reposted by Torr Vision Group Oxford

Lukas Aichberger @aichberger.bsky.social · 18/03/2025

⚠️ 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] 🧵

188

Reposted by Torr Vision Group Oxford

Fazl Barez @fbarez.bsky.social · 10/01/2025

🚨 New Paper Alert: Open Problem in Machine Unlearning for AI Safety 🚨 Can AI truly "forget"? While unlearning promises data removal, controlling emergent capabilities is a inherent challenge. Here's why it matters: 👇 Paper: arxiv.org/pdf/2501.04952 1/8

1256

Reposted by Torr Vision Group Oxford

Francesco Pinto @ Neurips2024 @frapintoml.bsky.social · 09/12/2024

🧵 [1/3] Heading to #Vancouver 🇨🇦 tomorrow to present our latest work in @OxfordTVG #UniversityOfOxford at #NeurIPS2024 🧠: - 💥 Improving on #StylizedImageNet, use #IllusionBench: can you see the cat 🐈‍⬛ Hidden in Plain Sight in the picture 🖼️? Paper: arxiv.org/abs/2411.06287

131