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.
arXiv:2507. 07754v3 Announce Type: replace-cross Abstract: Machine unlearning is usually evaluated by what the classifier outputs: forget-set accuracy, confidence, membership-inference scores.
arXiv:2606. 25001v1 Announce Type: new Abstract: Machine unlearning (MU) is commonly judged by output forgetting, such as low forget-set accuracy or reduced logit-level membership inference.
arXiv:2605. 20282v3 Announce Type: replace-cross Abstract: Machine unlearning in Vertical Federated Learning (VFL) has attracted growing interest, yet existing methods certify forgetting solely using output-level metrics.
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 what information must be preserved in replay buffers for class‑incremental learning. By treating cached predictions as temporally heterogeneous supervision, the authors separate classes known at storage time from those learned later, and evaluate the impact of deleting logit matching. Experiments on CIFAR‑100 with DER++ show that a simple task‑level offset can largely correct the cost of removing later‑class matching, while the cost of disrupting class correspondence remains.
arXiv:2605. 07482v2 Announce Type: replace Abstract: Machine unlearning for large language models (LLMs) aims to selectively remove memorized content such as private data, copyrighted text, or hazardous knowledge, without costly full retraining.
arXiv:2605. 20282v2 Announce Type: replace-cross Abstract: Machine unlearning in Vertical Federated Learning (VFL) has attracted growing interest, yet existing methods certify forgetting solely using output-level metrics.
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.
arXiv:2606. 06032v1 Announce Type: new Abstract: Catastrophic forgetting is commonly interpreted as the irreversible erasure of previously acquired knowledge during sequential learning.
arXiv:2607. 12204v1 Announce Type: new Abstract: Attention can be viewed as an online learner over context, yet existing test-time memories cannot certify that dropping a token leaves outputs unchanged or delete its influence outright.
arXiv:2605. 27569v2 Announce Type: replace Abstract: Machine unlearning aims to remove the influence of specific training records from a deployed model without retraining from scratch.
CALIBURN is a new approach to large language model (LLM) unlearning that measures a model’s confidence in undesirable knowledge and uses this measure to fine‑tune unlearning gradient updates. By doing so, it offers more precise control over what is forgotten while better preserving the model’s overall utility. Experiments on benchmarks such as MUSE and WMDP show that CALIBURN outperforms existing methods in balancing knowledge removal with utility retention.