Sign in

Anshuman Suri

@iamgroot42.bsky.social
45 followers 93 following 6 posts

Postdoc @ Khoury | Previously Ph.D. @ UVA (David Evans) | IIITD Alum | Interested in machine learning privacy & security.

PostsRepliesMedia
Anshuman Suri @iamgroot42.bsky.social · 18/12/2024
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 🧵
110
Anshuman Suri @iamgroot42.bsky.social · 26/11/2024
Temporally shifted data splits in membership inference can be misleading ⚠️ Be cautious when interpreting these benchmarks!
021