Source-Free Class Relearning: Diagnosing Forgetting in Class Unlearning

• URL: http://arxiv.org/abs/2609.02018v1
• Date: Wed, 02 Sep 2026 02:45:56 GMT
• Title: Source-Free Class Relearning: Diagnosing Forgetting in Class Unlearning
• Abstract summary: Class unlearning aims to remove a model's ability to recognize designated forget classes while preserving performance on retain classes.<n>We study class relearning in a strictly source-free setting, asking whether a forget class can be recovered using only the unlearned model.
• Score: 22.455121713091245
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Class unlearning aims to remove a model's ability to recognize designated forget classes while preserving performance on retain classes. However, low forget accuracy after unlearning does not necessarily mean the class structure has been erased. Approximate unlearning methods can alter classifier decision boundaries while leaving recoverable structure in the representation. Prior work has shown that forget classes can be recovered, but existing approaches require real forget or retain samples, auxiliary data, or reference checkpoints. We study class relearning in a strictly source-free setting, asking whether a forget class can be recovered through a classifier-head update using only the unlearned model. Our approach rests on a theoretical analysis establishing a sufficient alignment condition under which a single gradient step on a synthetic probe set increases the expected logit margin of the forget class. Building on this, we propose a white-box Source-Free Relearning Audit (SFRA), which generates candidate embeddings in representation space and uses model-guided confidence filtering to construct high-confidence retain probes and low-confidence boundary-adjacent probes that are relabelled as the forget class. Gaussian sampling and Softmax confidence are used by default, while ablations with alternative proposal distributions and uncertainty criteria show that recoverability is not specific to these choices. To quantify recoverability, we introduce the Relearning Score (RS), which jointly measures forget-class recovery and retain-accuracy preservation, and report class-matched $Δ$RS relative to a retrained reference. Experiments on CIFAR-10, CIFAR-100, and TinyImageNet with ResNet-18, ViT-B/16, and Swin-T show that several unlearning methods exhibit substantial source-free recoverability, and that for a subset of methods this recoverability exceeds the matched retrained reference.

Related papers

• Test-Time Unlearning via Sparse Autoencoder [55.4290003355764]
  We propose ARIA, a test-time unlearning method that leaves model weights intact and gates access to unwanted knowledge only when generation enters a forget-related state.<n>ARIA improves the forget-retain trade-off over weight-based baselines across both a thinking model and an instruction model.
  arXiv  Detail & Related papers  (2026-09-14T18:58:09Z)
• On-the-go Forgetting without Explicit Unlearning via ERASE [2.6426981014417046]
  ERASE is a framework for on-the-go forgetting that suppresses the observable influence of private data without modifying model weights.<n>We rigorously characterize sufficient conditions when ERASE provably achieves functional forgetting of designated subclasses.<n> ERASE maintains the best observed balance between forgetting efficacy, computational efficiency, and retention fidelity over recent unlearning-based methods.
  arXiv  Detail & Related papers  (2026-09-05T08:09:27Z)
• Measure, Don't Optimize: Forecasting Recovery in LLM Unlearning [57.920153607557744]
  J-Access is an inference-time audit that measures how often target concepts remain accessible along the model's output pathway.<n>We audit 398 public unlearned models spanning eight unlearning methods.
  arXiv  Detail & Related papers  (2026-08-11T20:16:20Z)
• Minimal Markovization via Stable Quotients in Holonomy-Cover Decision Processes [13.539613784615605]
  We describe a structured POMDP class in which the visible dynamics are RL and every realized visible transition applies a fixed permutation to a hidden mode.<n>We prove that the pair of current observation and stable class forms an exact finite Markov state.<n>Experiments recover an exact compression from raw states to quotient states and achieve perfect paired-order accuracy with three decision-time memory states.
  arXiv  Detail & Related papers  (2026-07-29T17:03:35Z)
• SAGE: Retain-Aware Post-Hoc Sanitization of Final Unlearning Vector [32.30497427199285]
  Current unlearning methods all involve a trade-off between unlearning and retention.<n>We have found that the retention activation bias can also be used to quantify the damage an unlearning method inflicts on retention.<n>This allows us to restore retention performance for any unlearning method using a post-hoc approach.
  arXiv  Detail & Related papers  (2026-06-16T08:29:43Z)
• An Illusion of Unlearning? Assessing Machine Unlearning Through Internal Representations [16.917151304941967]
  We show that state-of-the-art machine unlearning methods appear successful mainly due to a misalignment between last-layer features and the classifier.<n> hidden features remain highly discriminative, and simple linear probing can recover near-original accuracy.
  arXiv  Detail & Related papers  (2026-04-09T14:02:23Z)
• Suppression or Deletion: A Restoration-Based Representation-Level Analysis of Machine Unlearning [24.40457827994831]
  We propose a novel restoration-based analysis framework for machine unlearning.<n>Applying our framework to 12 major unlearning methods in image classification tasks, we find that most methods achieve high restoration rates.<n>We propose new evaluation guidelines that prioritize representation-level verification.
  arXiv  Detail & Related papers  (2026-02-18T07:46:30Z)
• Is Retain Set All You Need in Machine Unlearning? Restoring Performance of Unlearned Models with Out-Of-Distribution Images [0.0]
  We introduce Selective-distillation for Class and Architecture-agnostic unleaRning (SCAR) SCAR efficiently eliminates specific information while preserving the model's test accuracy without using a retain set. We experimentally verified the effectiveness of our method, on three public datasets.
  arXiv  Detail & Related papers  (2024-04-19T14:45:27Z)
• Rethinking Classifier Re-Training in Long-Tailed Recognition: A Simple Logits Retargeting Approach [102.0769560460338]
  We develop a simple logits approach (LORT) without the requirement of prior knowledge of the number of samples per class. Our method achieves state-of-the-art performance on various imbalanced datasets, including CIFAR100-LT, ImageNet-LT, and iNaturalist 2018.
  arXiv  Detail & Related papers  (2024-03-01T03:27:08Z)
• Mitigating Catastrophic Forgetting in Task-Incremental Continual Learning with Adaptive Classification Criterion [50.03041373044267]
  We propose a Supervised Contrastive learning framework with adaptive classification criterion for Continual Learning. Experiments show that CFL achieves state-of-the-art performance and has a stronger ability to overcome compared with the classification baselines.
  arXiv  Detail & Related papers  (2023-05-20T19:22:40Z)
• Queried Unlabeled Data Improves and Robustifies Class-Incremental Learning [133.39254981496146]
  Class-incremental learning (CIL) suffers from the notorious dilemma between learning newly added classes and preserving previously learned class knowledge. We propose to leverage "free" external unlabeled data querying in continual learning. We show queried unlabeled data can continue to benefit, and seamlessly extend CIL-QUD into its robustified versions.
  arXiv  Detail & Related papers  (2022-06-15T22:53:23Z)
• Online Selective Classification with Limited Feedback [82.68009460301585]
  We study selective classification in the online learning model, wherein a predictor may abstain from classifying an instance. Two salient aspects of the setting we consider are that the data may be non-realisable, due to which abstention may be a valid long-term action. We construct simple versioning-based schemes for any $mu in (0,1],$ that make most $Tmu$ mistakes while incurring smash$tildeO(T1-mu)$ excess abstention against adaptive adversaries.
  arXiv  Detail & Related papers  (2021-10-27T08:00:53Z)

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.