An Illusion of Unlearning? Assessing Machine Unlearning Through Internal Representations

2026-04-09

AI Summary

While existing machine unlearning methods appear effective at the output level, their internal representations often retain traces of the forgotten data, which can be easily recovered through fine-tuning, posing significant security risks. This work reveals that the apparent success of such methods typically stems from a misalignment between features and the classifier rather than genuine erasure of information. To address this, we propose a novel unlearning mechanism based on Class Mean Features (CMF), which leverages linear probing analysis and classifier adjustment grounded in the neural collapse hypothesis to achieve true forgetting at the representation level. Experiments demonstrate that CMF substantially reduces the recoverability of unlearned information while maintaining high accuracy on retained tasks, thereby validating the necessity and efficacy of representation-level unlearning evaluation.

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.

Problem

• machine unlearning
• internal representations
• feature-classifier misalignment
• neural collapse
• linear probing

Innovation

• machine unlearning
• internal representations
• feature-classifier misalignment
• class-mean features
• representation alignment