AI Paper Atlas

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

Fundamental Limits of Membership Inference Attacks on Machine Learning Models

Eric Aubinais, Elisabeth Gassiat, Pablo Piantanida

JMLR 2025 · Adversarial robustness and security › Attacks on text and graphs · approach: Membership inference and inversion · 10 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
discretize the data (cluster) before training, C_K(P)=4.303-layer network · MNIST (n=1000)accuracy: 0.989 -> 0.963Hurt
discretize the data with C_K(P)=6.74 or 9.203-layer network · MNIST (n=1000)accuracy: 0.989 -> 0.968 and 0.986Hurt
use a coarser discretization (smaller C_K(P), 4.3 vs 9.20) (ablation)3-layer network · MNIST (n=1000)security gap bound Delta: 0.15 -> 0.07Improved
use a coarser discretization (C_K(P)=4.3 vs 9.20) (ablation)3-layer network · MNIST (n=1000)accuracy: 0.986 -> 0.963Hurt
increase dataset size n from 1000 to 10000 (ablation)discretized MNIST, C_K(P)=4.3 · MNISTsecurity gap bound Delta: 0.07 -> 0.02Improved
increase dataset size n from 1000 to 10000 (ablation)raw MNIST network · MNISTaccuracy: 0.989 -> 0.994Improved
train to overfitting (2500 iterations) then apply loss-threshold attack2-layer ReLU network, regression · non-linear regressiontraining vs validation accuracy at eps=1e-6: 100% training vs near 0% validationHurt
increase input dimension from 10 to 2000 (ablation)overfitted linear regression · linear regressionvalidation accuracy at eps=1e-6No clear effect

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