arXiv:2606. 16110v1 Announce Type: new Abstract: Machine unlearning has been extensively studied in response to growing privacy concerns and regulatory requirements.
By Dayong Ye, Tianqing Zhu, Ruiding Huang, Xinbo Fu, Jiayang Li, Bo Liu, Huan Huo, Wanlei Zhou
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
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.
By Jonas Mirlach, Sonia Laguna, Julia E. Vogt
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
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.
By Aashiq Muhamed, Jacopo Bonato, Mona Diab, Virginia Smith