Machine Text Detectors are Membership Inference Attacks
From Google TechTalks · 1:00:14
Show by Google TechTalks
A Google TechTalk, 2026-02-04, presented by Ryoto KoikeABSTRACT: Although membership inference attacks (MIAs) and machine-generated text detection target different goals, their methods often exploit similar signals based on a language model’s probability distribution, and the two tasks have been studied independently. This can result in conclusions that overlook stronger methods and valuable insights from the other task. In this work, we theoretically and empirically demonstrate the transferability, i.e., how well a method originally developed for one task performs on the other, between MIAs and machine text detection. We prove that the metric achieving asymptotically optimal performance is identical for both tasks. We unify existing methods under this optimal metric and hypothesize that the accuracy with which a method approximates this metric is directly correlated with its transferability. Our large-scale empirical experiments demonstrate very strong rank correlation (ρ ≈ 0.7) in cross-task performance. Notably, we also find that a machine text detector achieves the strongest performance among evaluated methods on both tasks, demonstrating the practical impact of transferability. To facilitate cross-task development and fair evaluation, we introduce MINT, a unified evaluation suite for MIAs and machine-generated text detection, implementing 15 recent methods from both tasks (https://github.com/ryuryukke/MINT).Uploaded 09-06-26https://arxiv.org/abs/2510.19492
More episodes of Google TechTalks
More episodes
- DSD: A Hybrid Analysis Tool for Bug Finding
- Chasing the Constants and its Implications in Differential Privacy
- Making Great Decisions
- Streaming Private Continual Counting via Binning
- Distributed Testing with SmartFrog
- Differentially Private Synthetic Data without Training
- A Dynamic Network Layer for Advanced Cloud Computing
- Data Representation/Laplace Operator
- Persistent Pre-Training Poisoning of LLMs
- Threat Models for Memorization: Privacy, Copyright, and Everything In-Between
PodSearch is a free, independent podcast search engine. Read about PodSearch, the privacy policy or contact us.