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? ๐จ
tl;dr? It did ๐งต
Wrote a blurb for my submission "adversarial rinsing" ๐๐งผ to the 'Erasing the Invisible' competition organized by @bang_an_@furongh & co - awesome job btw! ๐
Ranked nowhere near the top lol but a great learning experience!
https://t.co/wfjj6lBx7o
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 @StoffelMPC read it. It's pretty accessible as long as you have high school to first 1 of uni math skills (calculus + linear algebra)
https://t.co/SlGbwakdcg
Thanks, @JaydeepBorkar! 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.
@EugeneVinitsky Something that worked for me when I was applying was following @UdacityDave blogpost on emailing potential advisors (https://t.co/HPcTVbhx3D) It has some great advice on doing your homework and writing a brief email :)
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.
๐ Join Our First Lego League Teams! ๐
๐น Division 1: One spot open for Grades 5 and 6!
๐น Division 2: Three spots open for Grades 7 and 8!
Don't miss the chance to be part of an exciting journey! ๐ค
Does white-box access help with membership inference? ๐ค
tl;dr: Yes โ
Come find Xiao (@xzhang_0427) at the High-dimensional Learning Dynamics (HiLD) Workshop at @icmlconf this Friday to learn more ๐๐
Prior works (@alexsablay et al. https://t.co/FOG0jz9gHB) theoretically show how black-box access is optimal for membership inference, and these findings seem to align with folklore and empirical observations around MIAs. However, the underlying assumptions for this theoretical result do not hold for models trained with SGD.
We theoretically show that parameter access helps. Our theory also prescribes an attack that can be used for privacy auditing without any reference models.
Read the full paper: https://t.co/Jhe6Dj0rY7
#ICML2024
@iamgroot42@KhouryCollege@Northeastern@AlinaMOprea Thanks so much, Dr. Suri - and congratulations on a terrific dissertation and outstanding presentation! It has been an honor to be part of your work, and I am excited for all the things you will do at @KhouryCollege and beyond.
๐ I'm thrilled to announce that I am joining the @EECS_UTK at the University of Tennessee, Knoxville as an Assistant Professor this fall. Grateful for all the support from my mentors and colleagues throughout my academic journey.
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 https://t.co/3tvQZ9Vheh .
Hurry, spots are filling up quickly!
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?
๐งต: Let's dive into some insights.
๐: https://t.co/jb58uIr8Uf
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 https://t.co/5yJ7mzB4xg.
Reach out if you are interested, and/or spread the word!