The paper presents a robust approximate unlearning method for Generalized Learning Vector Quantization (GLVQ) classifiers, enabling the removal of specific data samples from trained models. It evaluates how the size and characteristics of the forget set affect unlearning, proposes an adapted technique to mitigate instabilities, and demonstrates that the method achieves near-zero deviation from a fully retrained model while being up to 10^5 times more efficient on benchmark tabular datasets. The approach is applicable to any GLVQ model without altering its training scheme.
arXiv:2606. 16110v1 Announce Type: new Abstract: Machine unlearning has been extensively studied in response to growing privacy concerns and regulatory requirements.
The paper investigates whether a model that has undergone class unlearning can still recover forgotten classes without access to original data. It introduces a white‑box audit method that generates synthetic probes in representation space, filters them by confidence, and relabels boundary‑adjacent probes as the forgotten class. The authors define a Relearning Score to quantify recovery while preserving retain performance, and demonstrate that several unlearning techniques on CIFAR‑10, CIFAR‑100, and TinyImageNet can be fully recovered in a source‑free setting, sometimes even outperforming a retrained reference.
Machine unlearning has been extensively studied in response to growing privacy concerns and regulatory requirements. However, auditing whether unlearning algorithms have truly erased the influence of specific data remains an open challenge.
Reference-Guided Machine Unlearning (ReGUn) is a vision unlearning framework that prioritizes distributional indistinguishability over degradation-based heuristics. It uses disjoint held-out data to create a class-conditioned reference distribution for distillation, guiding forget samples toward non-member behavior without explicitly degrading predictions. Experiments across various architectures and datasets show that ReGUn achieves a competitive forgetting–utility trade-off and closely matches retrain-like membership inference behavior.
The paper investigates the feasibility of forget‑only unlearning, where a deletion algorithm can only access the trained model and the examples to forget, without any retained data or additional training information. It demonstrates that the possibility of successful unlearning depends on the learning method, showing that different datasets can yield identical models yet require distinct post‑deletion outputs. The authors establish lower bounds on the accuracy of unlearning relative to retraining and prove that, for certain learners, the algorithm must memorize a substantial portion of the training data—potentially the entire dataset—to handle arbitrary deletion requests, implying that models designed for forget‑only unlearning may need to retain more information than standard training does.
The paper introduces Dynamic DAE Guardrails (DSG), a method that uses Dynamic Sparse Autoencoders to perform precision unlearning in large language models. DSG leverages principled feature selection and a dynamic classifier to target activation-based unlearning, outperforming existing gradient‑based methods in terms of computational efficiency, stability, sequential unlearning, resistance to relearning attacks, data efficiency, and interpretability.
The paper introduces a concept-guided poisoning unlearning framework that explicitly identifies semantic concepts most strongly linked to a target class or knowledge. For image classification, it uses a Post-hoc Concept Bottleneck Model to locate relevant image regions and creates poisoned samples; for large language models, it aggregates Integrated Gradients over multiple question responses to mask important content and generate poisoned training targets. Experiments across several datasets demonstrate effective unlearning while largely preserving model utility.
arXiv:2607. 11975v1 Announce Type: cross Abstract: Current machine unlearning methods predominantly rely on global, coarse-grained intervention strategies.
The paper introduces Forgetting Only What Matters via Unlearning Layers (FOM-UL), a layer‑selective unlearning framework for large language models. FOM-UL uses a forget‑to‑retain significance score to identify transformer layers that strongly influence the forget set while being insensitive to the retain set, allowing targeted updates that preserve most of the model. Experiments on TOFU, KnowUnDo, and MUSE-style benchmarks show that FOM-UL reduces residual memorization and maintains utility better than several baselines, even after 8‑bit and 4‑bit post‑training quantization, and it also limits recovery of forgotten content in adversarial prompt tests.
arXiv:2507. 04219v5 Announce Type: replace-cross Abstract: Current unlearning methods for LLMs optimize on the private information they seek to remove by incorporating it into their fine-tuning data.
arXiv:2608. 16700v1 Announce Type: cross Abstract: Various machine unlearning techniques have been developed in response to privacy legislation requirements, enabling individuals to exercise their legal right to have their data $D_f$ removed from a machine learning model.
DecisionUnlearn-Bench is an empirical framework for evaluating machine unlearning in probabilistic decision models, comparing full, unlearned, and retain-only models across various deletion granularities, label renderings, and candidate sets. Experiments on the BANKING77 dataset show that full-to-oracle displacement increases from example to association to class deletion, and that replacing semantic option labels with opaque codes nearly eliminates the retrained oracle’s recognition of deleted classes. The study also highlights variability in unlearning performance across seeds, deletion targets, and datasets, underscoring the importance of reporting effect size, utility, robustness, and recoverability when assessing decision-model unlearning.