AI Paper Atlas

Research map / Adversarial robustness and security / Attacks on text and graphs

Scalable Membership Inference Attacks via Quantile Regression

Martin Andres Bertran, Shuai Tang, Aaron Roth, Michael Kearns, Jamie Heather Morgenstern, Steven Wu

NeurIPS 2023 · Adversarial robustness and security › Attacks on text and graphs · approach: Membership inference and inversion · 8 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use conditional quantile regression instead of a marginal thresholdMembership inference on CIFAR-10, CIFAR-100, and ImageNet-1k (ResNet-50 targets) · CIFAR-10 and CIFAR-100, 1% FPRprecision: 48.56% -> 62.95%; 58.81% -> 79.57%Improved
Use conditional quantile regression instead of a marginal thresholdMembership inference on ImageNet-1k ResNet-50 · ImageNet-1k, 1% and 0.1% FPRprecision: 47.62% -> 97.45%; 46.81% -> 99.64%Improved
Use quantile regression instead of LIRA shadow modelsMembership inference on ImageNet-1k ResNet-50 · ImageNet-1k, 1% and 0.1% FPRprecision: 94.57% -> 97.45%; 98.73% -> 99.64%Improved
Use quantile regression instead of LIRA shadow modelsMembership inference on CIFAR-10 and CIFAR-100 ResNet-50 · CIFAR-10 and CIFAR-100, 1% and 0.1% FPRprecision: 83.00% -> 62.95%; 93.70% -> 64.48%; 96.20% -> 79.57%; 99.02% -> 85.41%Hurt
Use one quantile regression model instead of LIRA ensemblesTabular membership inference · OpenML and ACS NYprecision: 83.35% vs 82.73%; 88.05% vs 90.31%; 87.35% vs 89.62%; 86.54% vs 79.57%; 67.31% vs 69.23%; 56.35% vs 52.53%; 63.98% vs 67Mixed
Increase the number of LIRA shadow modelsLIRA on OpenML and ACS NY · OpenML and ACS NYprecisionMixed
Use a shadow model architecture that mismatches the target architectureLIRA on CIFAR-10 and CIFAR-100 · CIFAR-10 and CIFAR-100precisionHurt
Minimize quantile-regression pinball loss on public dataMembership inference attacks across the evaluated datasets · Image and tabular experimentsprecisionImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy