Super stoked about this work!! (interesting problem *and* superb collaborators 😍) Turns out certain LLM training characteristics (*and the way we think of membership for generative models) make MI hard! Read more at: iamgroot42.github.io/mimir.github.i… (+ Michael Duan David Evans)

We're back from a lively break for the next session, starting with Anshuman Suri speaking about pitfalls in evaluating black-box attacks!

🌟 Dive into the world of coding this summer at Blue Ridge Boost! Let your child explore the fun and practical Python Camp in Charlottesville for ages 10-13. Engaging courses, expert instructors, and hands-on learning await! Sign up now for early bird discounts. #CodingAdventure

As an incoming Assistant Professor UVA CS, I invite applications for multiple PhD and internship positions! Seeking passionate individuals for interdisciplinary research in Software Engineering, Formal Methods, and Machine Learning. For more details, visit

Dive into the universe of LEGO Spike Essential at our new location on 2171 Ivy Road, Charlottesville, Virginia. Join us from June 17 to 21, 8:30 AM - 1:00 PM or 5:00 PM, for children aged 6 and 7. Explore more at our website (buff.ly/457yAOJ) #LEGO #SpikeEssential

Excited to share our work on data minimization for ML! The principle of data minimization is a cornerstone of global data protection regulations, but how do we implement it in ML contexts? 🧵: Let's dive into some insights. 🔗: arxiv.org/abs/2405.19471

The first two days of summer camp have been a smashing success! We still have spots available for next week, June 17 to June 21. Visit our website to sign-up buff.ly/3UU8onG . Hurry, spots are filling up quickly!

Congratulations Suya! Its been a privilege to advise you, and excited to see all the great things you will do at UTK!

David Evans Thanks Dave, it was also an honor to be advised you and YuanTian !

We will be closed the week of the Fourth of July. Camps will start on July 8 at 8:30 am. Join us for coding and robotics camps for kids aged 6 to thirteen from July 8 to August 16. Register at: buff.ly/3UU8onG Happy Fourth of July! #SummerCamps #CodingRoboticCamps

Our MIA evaluation research for LLMs has been accepted at Conference on Language Modeling! 🥳 It's time to think beyond just exact-record membership for privacy audits. Hope to see you in Philly soon! Meanwhile, check out this fascinating collection of related works that have emerged recently 👇

Does white-box access help with membership inference? 🤔 tl;dr: Yes ✅ Come find Xiao (Xiao Zhang) at the High-dimensional Learning Dynamics (HiLD) Workshop at ICML Conference this Friday to learn more 📊🔍 Prior works (Alex Sablayrolles et al. proceedings.mlr.press/v97/sablayroll…) theoretically

🌟 Join Our First Lego League Teams! 🚀 🔹 Division 1: One spot open for Grades 5 and 6! 🔹 Division 2: Three spots open for Grades 7 and 8! Don't miss the chance to be part of an exciting journey! 🤖

Meet Assistant Professor Fnu Suya. His research interests include the application of machine learning techniques to security-critical applications and the vulnerabilities of machine learning models in the presence of adversaries, generally known as trustworthy machine learning.

I’m recruiting PhD students interested in trustworthy ML and ML for security this cycle! Please reach out via email anytime or find me at ACM CCS 2025 next week. Retweets are greatly appreciated!

Thanks, Jaydeep Borkar! I should probably update that someday - its more than 20 years old now, but mostly still true. Even harder now for new students to get an email noticed with all the GPT-generated emails around now, but can still make it clear you've put in some effort.

Best book to started is A Pragmatic Introduction to Secure Computation Despite working on MPC for almost 4 years, I refer to this pretty regularly and have my staff at both HashCloak and Stoffel MPC read it. It's pretty accessible as long as you have high school to first 1 of

Wrote a blurb for my submission "adversarial rinsing" 😈🧼 to the 'Erasing the Invisible' competition organized by Bang An Furong Huang & co - awesome job btw! 🎉 Ranked nowhere near the top lol but a great learning experience! anshumansuri.com/post/eti/

Temporally shifted data splits in membership inference can be misleading ⚠️ Be cautious when interpreting these benchmarks!

1/ Most membership inference attacks (MIAs) have seemingly converged to black-box settings, driven by empirical evidence and theoretical folklore suggesting black-box access was optimal. But what if this assumption missed something critical? 😨 tl;dr? It did 🧵