AI Paper Atlas

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

Unlearning’s Blind Spots: Over‑Unlearning and Prototypical Relearning Attack

SeungBum Ha, Saerom Park, Sung Whan Yoon

ICML 2026 · Adversarial robustness and security › Attacks on text and graphs · approach: Membership inference and inversion · 0 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 Spotter regularizers to SalUnSalUn · CIFAR-10 (one class unlearned)OU@epsilon: 0.1664 -> 0.0345Improved
add Spotter regularizers to DELETEDELETE · CIFAR-10 (one class unlearned)OU@epsilon: 0.1216 -> 0.0232Improved
add Spotter regularizers to UNSCUNSC · CIFAR-10 (one class unlearned)OU@epsilon: 0.1575 -> 0.0089Improved
add Spotter regularizers to SalUnSalUn · CIFAR-10 (one class unlearned)Proto-Acc_f: 95.34 -> 0.34Improved
add Spotter regularizers to UNSCUNSC · CIFAR-100 (ten classes unlearned)Proto-Acc_f: 73.62 -> 18.54Improved
add over-unlearning loss L_o (lambda1 from 1 to 0.7) to SalUn + Spotter (ablation)SalUn + Spotter · CIFAR-10 (one class unlearned), lambda2=0OU@epsilon: 0.1864 -> 0.0335Improved
add L_o (lambda1 from 1 to 0.3) to Spotter with lambda2=1 (ablation)Spotter · CIFAR-10 (one class unlearned)OU@epsilon: 0.0485 -> 0.0197Improved
add dispersion loss L_sim (lambda2 from 0 to 1) to Spotter lambda1=0.7 (ablation)Spotter · CIFAR-10 (one class unlearned)Proto-Acc_f: 99.70 -> 0.26Improved
add dispersion loss L_sim (lambda2 from 0 to 1) to Spotter lambda1=0.7 (ablation)Spotter · CIFAR-10 (one class unlearned)Acc_rt: 94.19 -> 93.91Hurt
increase lambda2 from 1 to 2 for Spotter lambda1=1 (ablation)Spotter · CIFAR-10 (one class unlearned)Acc_rt: 93.71 -> 91.93Hurt
apply Spotter to pretrained CLIP ViT-B/32CLIP ViT-B/32 · ImageNet class unlearningAcc_ft: 54.18 -> 0.00Improved
add Spotter to SalUn on retained test accuracySalUn · CIFAR-10 (one class unlearned)Acc_rt: 89.09 -> 93.37Improved

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