An Illusion of Unlearning? Assessing Machine Unlearning Through Internal Representations

• URL: http://arxiv.org/abs/2604.08271v1
• Date: Thu, 09 Apr 2026 14:02:23 GMT
• Title: An Illusion of Unlearning? Assessing Machine Unlearning Through Internal Representations
• Abstract summary: 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.
• Score: 16.917151304941967
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While numerous machine unlearning (MU) methods have recently been developed with promising results in erasing the influence of forgotten data, classes, or concepts, they are also highly vulnerable-for example, simple fine-tuning can inadvertently reintroduce erased concepts. In this paper, we address this contradiction by examining the internal representations of unlearned models, in contrast to prior work that focuses primarily on output-level behavior. Our analysis shows that many state-of-the-art MU methods appear successful mainly due to a misalignment between last-layer features and the classifier, a phenomenon we call feature-classifier misalignment. In fact, hidden features remain highly discriminative, and simple linear probing can recover near-original accuracy. Assuming neural collapse in the original model, we further demonstrate that adjusting only the classifier can achieve negligible forget accuracy while preserving retain accuracy, and we corroborate this with experiments using classifier-only fine-tuning. Motivated by these findings, we propose MU methods based on a class-mean features (CMF) classifier, which explicitly enforces alignment between features and classifiers. Experiments on standard benchmarks show that CMF-based unlearning reduces forgotten information in representations while maintaining high retain accuracy, highlighting the need for faithful representation-level evaluation of MU.

Related papers

• HSFM: Hard-Set-Guided Feature-Space Meta-Learning for Robust Classification under Spurious Correlations [25.503211313768062]
  We propose a bilevel meta-learning method that performs augmentation directly in feature space to improve spurious correlation handling in the classifier head.<n>By operating at the backbone output rather than in pixel space, the method is highly efficient and stable, requiring only a few minutes of training on a single GPU.
  arXiv  Detail & Related papers  (2026-03-31T06:32:56Z)
• Decoding the Critique Mechanism in Large Reasoning Models [50.821607345799386]
  Large Reasoning Models (LRMs) exhibit backtracking and self-verification mechanisms that enable them to revise intermediate steps and reach correct solutions.<n>We investigate how current LRMs recover from errors by inserting arithmetic mistakes in their intermediate reasoning steps.<n>We find that despite the error propagating through the chain-of-thought, the model still reaches the correct final answer.
  arXiv  Detail & Related papers  (2026-03-17T10:03:30Z)
• 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)
• Reference-Specific Unlearning Metrics Can Hide the Truth: A Reality Check [60.77691669644931]
  We propose Functional Alignment for Distributional Equivalence (FADE), a novel metric that measures distributional similarity between unlearned and reference models.<n>We show that FADE captures functional alignment across the entire output distribution, providing a principled assessment of genuine unlearning.<n>These findings expose fundamental gaps in current evaluation practices and demonstrate that FADE provides a more robust foundation for developing and assessing truly effective unlearning methods.
  arXiv  Detail & Related papers  (2025-10-14T20:50:30Z)
• LLM Unlearning on Noisy Forget Sets: A Study of Incomplete, Rewritten, and Watermarked Data [69.5099112089508]
  Large language models (LLMs) exhibit remarkable generative capabilities but raise ethical and security concerns by memorizing sensitive data.<n>This work presents the first study of unlearning under perturbed or low-fidelity forget data, referred to as noisy forget sets.<n>We find that unlearning remains surprisingly robust to perturbations, provided that core semantic signals are preserved.
  arXiv  Detail & Related papers  (2025-10-10T05:10:49Z)
• Unlearning Isn't Deletion: Investigating Reversibility of Machine Unlearning in LLMs [38.837810490068556]
  Unlearning in large language models (LLMs) aims to remove specified data, but its efficacy is typically assessed with task-level metrics like accuracy and perplexity.<n>We demonstrate that models can appear to forget while their original behavior is easily restored through minimal fine-tuning.<n>This phenomenon of emphreversibility suggests that information is merely suppressed, not genuinely erased.
  arXiv  Detail & Related papers  (2025-05-22T16:02:10Z)
• Probably Approximately Precision and Recall Learning [60.00180898830079]
  A key challenge in machine learning is the prevalence of one-sided feedback.<n>We introduce a Probably Approximately Correct (PAC) framework in which hypotheses are set functions that map each input to a set of labels.<n>We develop new algorithms that learn from positive data alone, achieving optimal sample complexity in the realizable case.
  arXiv  Detail & Related papers  (2024-11-20T04:21:07Z)
• 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)
• Learning the Unlearned: Mitigating Feature Suppression in Contrastive Learning [45.25602203155762]
  Self-Supervised Contrastive Learning has proven effective in deriving high-quality representations from unlabeled data. A major challenge that hinders both unimodal and multimodal contrastive learning is feature suppression. We propose a novel model-agnostic Multistage Contrastive Learning framework.
  arXiv  Detail & Related papers  (2024-02-19T04:13:33Z)
• Learning Prompt-Enhanced Context Features for Weakly-Supervised Video Anomaly Detection [37.99031842449251]
  Video anomaly detection under weak supervision presents significant challenges. We present a weakly supervised anomaly detection framework that focuses on efficient context modeling and enhanced semantic discriminability. Our approach significantly improves the detection accuracy of certain anomaly sub-classes, underscoring its practical value and efficacy.
  arXiv  Detail & Related papers  (2023-06-26T06:45:16Z)
• Measuring Self-Supervised Representation Quality for Downstream Classification using Discriminative Features [56.89813105411331]
  We study the representation space of state-of-the-art self-supervised models including SimCLR, SwaV, MoCo, BYOL, DINO, SimSiam, VICReg and Barlow Twins. We propose Self-Supervised Representation Quality Score (or Q-Score), an unsupervised score that can reliably predict if a given sample is likely to be mis-classified. Fine-tuning with Q-Score regularization can boost the linear probing accuracy of SSL models by up to 5.8% on ImageNet-100 and 3.7% on ImageNet-1K.
  arXiv  Detail & Related papers  (2022-03-03T17:48:23Z)
• Prototypical Classifier for Robust Class-Imbalanced Learning [64.96088324684683]
  We propose textitPrototypical, which does not require fitting additional parameters given the embedding network. Prototypical produces balanced and comparable predictions for all classes even though the training set is class-imbalanced. We test our method on CIFAR-10LT, CIFAR-100LT and Webvision datasets, observing that Prototypical obtains substaintial improvements compared with state of the arts.
  arXiv  Detail & Related papers  (2021-10-22T01:55:01Z)

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.