Stochastic Squirrel 🐿️

Random stack of interesting information "nuts"


Reassessing EMNLP 2024’s Best Paper: Does Divergence-Based Calibration for Membership Inference Attacks Hold Up?

TL;DR: No.
A critical analysis of the EMNLP Best Paper proposing a divergence-based calibration for Membership Inference Attacks (MIAs). We explore its experimental shortcomings, issues with temporally shifted benchmarks, and what this means for machine learning awards.

11 min read   ·   2024

My submission to the MICO Challenge

Description of my entry to the MICO challenge (co-located with SaTML) for membership inference that won me the 2nd place on the CIFAR track.

36 min read   ·   2023

Running scripts on Rivanna at UVA

A tutorial on how to run scripts on Rivanna (SLURM in general) cluster at UVA, along with some tricks.

13 min read   ·   2022