Matthieu Meeus (@matthieu_meeus) 's Twitter Profile
Matthieu Meeus

@matthieu_meeus

PhD student @ImperialCollege - Privacy & AI - matthieumeeus.com

ID: 1569718344546402304

calendar_today13-09-2022 16:03:24

104 Tweet

184 Takipçi

488 Takip Edilen

Matthieu Meeus (@matthieu_meeus) 's Twitter Profile Photo

Check out our recent work on prompt injection attacks! Tl;DR: aligned LLMs show to defend against prompt injection; yet with a strong attacker (GCG on steroids), we find that successful attacks (almost) always exist, but are just harder to find. arxiv.org/pdf/2505.15738