In America you have to check power outages on a hamburger app because the privately owned utilities are incompetent

Will be at ICML Conference 2024 in Vienna next week! Come check out our conference poster on how network linearization may lead to disparate impacts on different groups (link to the paper below) and feel free to hit me up for a chat :) See you all there! arxiv.org/abs/2402.03629 #ICML

NeurIPS reviewer: solution is not new and was heavily studied. NeurIPS Conference #NeurIPS24

Thrilled to share my discovery on bypassing Meta's Prompt-Guard! Excited to contribute to AI safety. For more details, check out The Register article theregister.com/2024/07/29/met…. Thanks Sukriti Paul for the shoutout! #AIResearch #PromptGuard #ResponsibleAI #AI #LLMs

LLMs o7

Just released: FRACTURED-SORRY-Bench 🧩 A new dataset and framework for exploring AI safety through malicious intent decomposition. We found some interesting insights by bypassing safety measures 6x. Curious? Check out the full blog! amanpriyanshu.github.io/blogs/posts/20… #jailbreak #LLM

This is still the funnest tweet I’ve ever seen on this platform

It is under-appreciated that -thinking- is a social activity. The best ideas I have had are in conversation. This is one of the most important reasons to schedule regular research meetings, even when it seems like there aren't lots of new developments to talk about.

do you ever remember how cool being a researcher is because you just get to wake up and work on whatever you want to all day and then do it again tomorrow cause I do

The answer, of course, is a subtle mix of psychological aspects (improved self-confidence & self-worth), material aspects (a nice apartment and a permanent job), scientific aspects (the gradual build-up of my intuition). The latter aspect shouldn’t be overestimated.

We’re excited to announce that the AAAI Workshop on Privacy-Preserving Artificial Intelligence (PPAI-25) is back! 🔗 ppai-workshop.github.io Please share widely! 🙏 Hosted at the 39th AAAI Conference on Artificial Intelligence (AAAI-25), this workshop will bring together AI

We are excited to share the first chapter of the book, "Differential Privacy in Artificial Intelligence: From Theory to Practice", which I have co-edited with Pascal Van Hentenryck, and is being published. This chapter, co-authored with @PVanHentenryck and @JubaZiani, offers a

It’s the season of “finding ur next adventure” and folks have been asking me about my experience doing a postdoc, so I did a blog post/video w/ Sasha Rush 's help! Should I do a postdoc? What is a postdoc anyway? youtu.be/O7psT1ftwqs Blog: homes.cs.washington.edu/~niloofar/blog…

Deadline extended! The AAAI Workshop on Privacy-Preserving Artificial Intelligence (PPAI-25) (ppai-workshop.github.io) is now accepting papers until November 29, 2024. Submit your best work! x.com/nandofioretto/…

🆘Help needed! Are you working on Privacy (from a Technical (e.g., Differential Privacy), Policy, or Law perspective)? Please give your availability to review for PPAI (ppai-workshop.github.io) if you can! We'd highly appreciate it! 🙏 forms.gle/dqjVsBsR2y81v1…

Honestly one of the best (if not *the* best) shows ever made in this lifetime!!! Now we wait for the Noxian lore to cross paths with Piltover’s 👊

“Ma Meilleure Ennemie” by Stromae & Pomme enters the top 10 on global Spotify at #8 (+17) with 5.972 million streams.

I’ll be at Johns Hopkins next week, talking about privacy, memorization and language models! Join us!

Congratulations to James Kotary for successfully defending his dissertation with flying colors! 👏🔥🎉 His research integrates ML and optimization, advancing both optimization algs and the reasoning in ML models. Check out his work: j-kota.github.io I am proud advisor :)