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.
By Luka Radi\'c, Vikrant Singhal, Amartya Sanyal
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.
By Jaeheun Jung, Bosung Jung, Suhyun Bae, Donghun Lee
arXiv:2609.37076v1 Announce Type: new
Abstract: Large language models trained on vast corpora inherently risk memorizing harmful content that may later re-emerge in their outputs. To mitigate this is...
By Puning Yang, Qizhou Wang, Junchi Yu, Bo Han, Xiuying Chen
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.
By Jonas Mirlach, Sonia Laguna, Julia E. Vogt
The paper introduces Kernel-Anticipated Unlearning (KAU), a method for approximate unlearning of knowledge-graph embeddings that accounts for relearning during continued training. KAU uses the tangent kernel to model how forgotten facts’ scores change, expressing this response in closed form and guiding edits to minimize future leakage. Experiments show KAU reduces leakage by 46‑63% on FB15k-237 and 50‑82% on CoDEx-L compared to the strongest existing unlearner, while preserving higher utility.
By Parnian Fazel, Mohammad M Maheri, Hamed Haddadi
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.
By Wenhan Chang, Tianqing Zhu, Heng Xu, Wenjian Liu, Wanlei Zhou
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.
By Teresa Pui Yee Yong, Win Kent Ong, Chee Seng Chan
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.
By Zahra Dehghani, Pablo Piantanida, Mohammadhadi Shateri
arXiv:2503. 18314v5 Announce Type: replace-cross Abstract: We present LoTUS, a novel Machine Unlearning (MU) method that eliminates the influence of training samples from pre-trained models, avoiding retraining from scratch.
By Christoforos N. Spartalis, Theodoros Semertzidis, Petros Daras, Efstratios Gavves
The paper introduces Unmerge, an efficient machine unlearning algorithm that treats unlearning as the inverse of task arithmetic. By representing the forget component as a low‑rank basis at each layer, Unmerge optimizes three goals—matching the merged vector, suppressing leakage, and bounding correction size—to limit forget leakage and retain damage. Experiments on ResNet‑50, ViT‑S/16, and Llama‑3.2‑3B show significant performance gains over existing methods while maintaining privacy and feature‑distribution fidelity.
By Haoran Tang, Andrew Tan, Rajiv Khanna
The paper investigates what a service must retain to faithfully reproduce a training pipeline after data deletion requests, focusing on a rule where earlier similar records block later ones. It shows that a limit on future deletions precisely determines which records can still be needed for training, enabling an exact repair of training statistics after repeated deletions. The authors also construct finite‑precision features for ridge regression and demonstrate that the required private information can be minimized across a sequence of deletion requests, validating their approach on 1,001 AskUbuntu records.
By Priyank Jayraj, Devanshu sahoo, Uday Mittal
The paper highlights that current deep machine unlearning research focuses on overall effectiveness, neglecting how difficult it is to unlearn individual training samples. It presents a detailed instance-level performance analysis across various algorithms and datasets, identifying four factors that make unlearning a data point hard. The study shows these factors are independent of the unlearning method but depend on the target model and its training data, urging future research to consider instance-level difficulty.
By Hammad Rizwan, Mahtab Sarvmaili, Hassan Sajjad, Ga Wu