SOURCE-LINKED INTELLIGENCE

Membership Inference via Pairwise Likelihood Ratios

arXiv · AI, language, vision and robotics · article · Sep 11, 2026 · UTC

Membership inference attacks (MIAs) are the standard tool for auditing the privacy risks of machine learning models. Given a query point, an MIA aims to determine whether that point was used to train the target model. In practice, such inference must rely on the statistical signals exposed by the model's outputs, such as confidence scores, logits, and intermediate feature representations. However, existing methods often fail to efficiently summarize and combine these statistical signals. To address this limitation, we propose Pairwise Likelihood MIA (PL-MIA), a unified method that combines a G

Read original source ↗ Open in workspace

recordType

paper

region

Global