PURGE: Projected Unlearning via Retain-Guided Erasure

• URL: http://arxiv.org/abs/2606.03808v1
• Date: Tue, 02 Jun 2026 15:53:01 GMT
• Title: PURGE: Projected Unlearning via Retain-Guided Erasure
• Abstract summary: PURGE is a machine unlearning algorithm built on a simple but an under-exploited observation: continual learning (CL) and machine unlearning (MU)<n> CL tries to learn new tasks without forgetting old ones; MU tries to erase specific data without hurting retained performance representing the same underlying tension in opposite directions.<n> PURGE consistently keeps accuracy above 96% while achieving MIA AUROC close to 0.5 (the ideal), outperforming gradient ascent, KL-uniform, and several published baselines on the privacy-utility frontier.
• Score: 5.069332646113575
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We propose PURGE, a machine unlearning algorithm built on a simple but an under-exploited observation: continual learning (CL) and machine unlearning (MU) which are fundamentally dual problems. CL tries to learn new tasks without forgetting old ones; MU tries to erase specific data without hurting retained performance representing the same underlying tension in opposite directions. PURGE leverages this duality by adapting gradient projection from A-GEM (Chaudhry et al., 2019) so that every unlearning step is constrained to not increase the retain-set loss. On top of this, it performs multi-layer representation erasure, pushing forget-set activations in intermediate layers towards the retain distribution to remove information from hidden representations rather than just suppressing it at the output. A key design choice is the retain-confusion target: rather than pushing forget outputs toward the uniform distribution, which we found to be surprisingly easy for membership inference attacks to detect, we instead target the model's natural confusion pattern on retain data. This makes the unlearned model hard to distinguish from one retrained from scratch. Two self-regulating stopping criteria (a retain-loss budget and a forget-accuracy target) let the algorithm decide on its own when to stop, removing the need for manual epoch tuning. In experiments on five datasets (CIFAR-10, MNIST, SVHN, STL10, PathMNIST) across 22 class-level forgetting tasks, PURGE consistently keeps retain accuracy above 96% while achieving MIA AUROC close to 0.5 (the ideal), outperforming gradient ascent, KL-uniform, and several published baselines on the privacy-utility frontier.

Related papers

• ReDraft, Don't Just Distill: Reference-Driven Revision for Continual VLLM Post-Training [66.72708893922605]
  Post-training of large multimodal models should add new capabilities while preserving those from pre-training.<n>SFT gives explicit target supervision that learns a task from near-zero accuracy, but its off-policy targets move the model far enough to cause forgetting.<n>We introduce ReDraft, which obtains both from the model's own failures.
  arXiv  Detail & Related papers  (2026-09-15T04:59:03Z)
• How Hard Can It Be? Hardness-Aware Multi-Objective Unlearning [75.97729821186815]
  Machine unlearning aims to remove the influence of specific forget training data due to privacy, copyright or bias concerns.<n>We derive an unlearning algorithm with the overall goal of guaranteeing a specified improvement in forget quality.<n>Our hardness measure informs users when retain utility degradation is unavoidable.
  arXiv  Detail & Related papers  (2026-06-01T11:49:47Z)
• SHRED: Retain-Set-Free Unlearning via Self-Distillation with Logit Demotion [39.17638540496959]
  SHRED (Self-distillation via High-surprisal-only Retain-set-free Entropy Demotion) is a retain-set-free unlearning method built on a key insight.<n>High-information tokens concentrate the model's memorized knowledge, while low-information tokens reflect general language competence.<n> SHRED is robust against relearning attacks and membership-inference attacks, and it maintains stable utility even after many sequential unlearning runs.
  arXiv  Detail & Related papers  (2026-05-08T09:25:18Z)
• Retain-Neutral Surrogates for Min-Max Unlearning [6.039098328985986]
  Machine unlearning seeks to remove the influence of designated training data while preserving performance on the remaining data.<n>In min-max unlearning, the key local object is the surrogate point at which the retain objective is evaluated.<n>We propose Retain-Orthogonal Surrogate Unlearning, which constrains the inner surrogate construction by maximizing first-order forget gain.
  arXiv  Detail & Related papers  (2026-05-07T08:38:09Z)
• Geometric-Disentangelment Unlearning [106.99160454669902]
  gradient ascent on forget samples often harms retained knowledge.<n>We propose the Geometric-disment Unlearning (GU) that decomposes any candidate forget gradient update into tangential and normal components to retain space and executes only the normal component.<n>Our method is plug-and-play and can be attached to existing gradient-based unlearning procedures to mitigate side effects.
  arXiv  Detail & Related papers  (2025-11-21T09:58:25Z)
• Constrained Entropic Unlearning: A Primal-Dual Framework for Large Language Models [14.321060805197874]
  Large Language Models (LLMs) deployed in real-world settings increasingly face the need to unlearn sensitive, outdated, or proprietary information.<n>Existing unlearning methods formulate forgetting and retention as a regularized trade-off, combining both objectives into a single scalarized loss.<n>We propose a new formulation of LLM unlearning as a constrained optimization problem: forgetting is enforced via a novel logit-margin flattening loss.
  arXiv  Detail & Related papers  (2025-06-05T17:55:23Z)
• Train with Perturbation, Infer after Merging: A Two-Stage Framework for Continual Learning [57.514786046966265]
  We propose textbfPerturb-and-Merge (P&M), a novel continual learning framework that integrates model merging into the CL paradigm to mitigate forgetting.<n>Our proposed approach achieves state-of-the-art performance on several continual learning benchmark datasets.
  arXiv  Detail & Related papers  (2025-05-28T14:14:19Z)
• Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement [29.675650285351768]
  Machine unlearning (MU) has emerged to enhance the privacy and trustworthiness of deep neural networks. Approximate MU is a practical method for large-scale models. We propose a fast-slow parameter update strategy to implicitly approximate the up-to-date salient unlearning direction.
  arXiv  Detail & Related papers  (2024-09-29T15:17:33Z)
• Adaptive Retention & Correction: Test-Time Training for Continual Learning [114.5656325514408]
  A common problem in continual learning is the classification layer's bias towards the most recent task.<n>We name our approach Adaptive Retention & Correction (ARC)<n>ARC achieves an average performance increase of 2.7% and 2.6% on the CIFAR-100 and Imagenet-R datasets.
  arXiv  Detail & Related papers  (2024-05-23T08:43:09Z)
• Deep Unlearning: Fast and Efficient Gradient-free Approach to Class Forgetting [9.91998873101083]
  We introduce a novel class unlearning algorithm designed to strategically eliminate specific classes from the learned model. Our algorithm exhibits competitive unlearning performance and resilience against Membership Inference Attacks (MIA)
  arXiv  Detail & Related papers  (2023-12-01T18:29:08Z)
• Two-phase Pseudo Label Densification for Self-training based Domain Adaptation [93.03265290594278]
  We propose a novel Two-phase Pseudo Label Densification framework, referred to as TPLD. In the first phase, we use sliding window voting to propagate the confident predictions, utilizing intrinsic spatial-correlations in the images. In the second phase, we perform a confidence-based easy-hard classification. To ease the training process and avoid noisy predictions, we introduce the bootstrapping mechanism to the original self-training loss.
  arXiv  Detail & Related papers  (2020-12-09T02:35:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.