AI Paper Atlas

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

Unlearning with Asymmetric Sources: Improved Unlearning-Utility Trade-off with Public Data

Ahmed Mehdi Inane, Vincent Quirion, Gintare Karolina Dziugaite, Ioannis Mitliagkas

ICML 2026 · Federated learning and privacy › Privacy attacks and secure learning · approach: Encryption-based private learning

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 50000 Amazon Reviews public pointsLangevin Unlearning · IMDB (LSTM, K=15)unlearned test accuracy: 82.59 -> 81.42Hurt
flip 40% of public labels (more mismatch) versus clean public data (ablation)ALU · IMDB (LSTM, K=15)unlearned test accuracy: 1.17% -> 2.19%Hurt
flip 40% of public labels versus clean public data (ablation)ALU retrained model · IMDB (LSTM, K=15)retrained test accuracy: 0.39% -> 1.74%Hurt
increase public points from 10000 to 40000 with aligned domains (ablation)ALU · DomainNet aligned (Quickdraw public, Clipart private, K=5)relative loss difference (%): 4.23 -> 3.68No clear effect
increase public points from 10000 to 40000 with misaligned domains (ablation)ALU · DomainNet misaligned (Infograph public, Real private, K=5)relative loss difference (%): 10.53 -> 10.81No clear effect
misaligned instead of aligned public-private domains (ablation)ALU · DomainNet (K=5)relative loss difference (%): 4.23 -> 10.53Hurt
add public data to Langevin unlearningLU · DomainNet ClipartRenyi divergence to retrainingImproved
add public data to Langevin unlearningLU · IMDB with U-LiRAU-LiRA confidenceImproved

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