AI Paper Atlas

Research map / Federated learning and privacy / Privacy attacks and secure learning

Active Membership Inference Test (aMINT): Enhancing Model Auditability with Multi-Task Learning.

Daniel DeAlcala, Aythami Morales, Julian Fierrez, Gonzalo Mancera, Ruben Tolosana, Javier Ortega-Garcia

ICCV 2025 · Federated learning and privacy › Privacy attacks and secure learning · approach: Encryption-based private learning · 5 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
add middle-setup AAD instead of entry (ablation)Active MINT ResNet50 · CIFAR-10MINT accuracy: 0.86 -> 0.89Improved
use output-setup AAD instead of entry (ablation)Active MINT ResNet50 · CIFAR-10audited accuracy: 0.53 -> 0.39Hurt
use output-setup AAD instead of entry (ablation)Active MINT ResNet50 · CIFAR-10MINT accuracy: 0.86 -> 0.85Hurt
use entry-setup AAD instead of middle (ablation)Active MINT ResNet50 · GTSRBMINT accuracy: 0.83 -> 0.86Improved
train MINT model jointly (Active) instead of post hoc (Passive)ResNet50 · CIFAR-10MINT accuracy: 0.66 -> 0.86Improved
train MINT model jointly (Active) instead of post hoc (Passive)ResNet50 · MNISTMINT accuracy: 0.51 -> 0.83Improved
train MINT model jointly (Active) instead of post hoc (Passive)ResNet50 · GTSRBMINT accuracy: 0.61 -> 0.86Improved
train MINT model jointly (Active) instead of post hoc (Passive)ResNet50 · Tiny ImageNetMINT accuracy: 0.59 -> 0.80Improved
train MINT model jointly (Active) instead of post hoc (Passive)ViT · CIFAR-10MINT accuracy: 0.60 -> 0.86Improved
train MINT model jointly with the audited modelResNet50 · CIFAR-10audited accuracy: 0.55 -> 0.53Hurt
train MINT model jointly with the audited modelResNet50 · Tiny ImageNetaudited accuracy: 0.17 -> 0.12Hurt
train MINT model jointly with the audited modelMobileNet · MNISTaudited accuracy: 0.97 -> 0.96Hurt

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