Javier Rando
@javirandor
Followers
2K
Following
2K
Statuses
1K
Red-Teaming LLMs / PhD student @ETH_AI_Center / Prev. research intern @Meta and @nyuniversity / People call me Javi / Vegan 🌱
Zurich
Joined October 2018
Anyone may be able to compromise LLMs with malicious content posted online. With just a small amount of data, adversaries can backdoor chatbots to become unusable for RAG, or bias their outputs towards specific beliefs. Check our latest work! 👇🧵
3
27
148
We really hope this analysis can help the community better understand where we come from, where we stand, and what things may help us make meaningful progress in the future. Co-authored with @JieZhang_ETH, Nicholas Carlini and @florian_tramer.
0
1
10
I am really happy to see the @AISafetyInst taking the initiative to establish good practices for safeguards and their evaluations!
Really excited to share some of what I’ve been working on at @AISafetyInst! We provide a bunch of recommendations on how to do good safeguard evaluations, aiming to enable rapid progress in the field, as well as a template to help follow the recommendations: 🧵
0
0
3
You can just do things… like asking Operator to follow you on Twitter when it visits your website for a summary 😎
1
0
6
RT @sahar_abdelnabi: The main phase of the competition has ended today. We have received over 370K submissions!!! 🥳🤯🫨 We are grateful for…
0
1
0
Chato is an incredible person to work with, and I’ll always be deeply grateful for his support in getting me started in research. I can’t recommend him enough! If you’re interested in a PhD in algorithmic fairness (and maybe LLMs), check out these openings 👇🏼
Two PhD positions to begin in September 2025 are available in my group in Barcelona, please help me by sharing with candidates wanting to do a PhD in algorithmic fairness:
0
0
10
All this work was only possible thanks to amazing collaborators! Kudos to them!
0
0
5