04:00
2026-10-05
machinebrief.com
artificial-intelligence
OLMo-Detect: A Multi-Stage, Confounder-Controlled Benchmark for Membership Inference on Large Language Models
A new benchmark called OLMo-Detect, built on the fully open OLMo 2 pipeline, finds that membership inference attacks on large language models remain weak, with the best unsupervised and supervised att…