The paper introduces MUNKEY, a memory‑augmented transformer that enables machine unlearning by design. By decoupling instance‑specific memorization from model weights, unlearning is achieved simply by deleting an instance‑identifying key, allowing zero‑shot forgetting without retraining or accessing original data. Experiments on natural image, fine‑grained visual recognition, and medical datasets show that MUNKEY outperforms existing post‑hoc unlearning methods while maintaining predictive performance.
By Sonia Laguna, Jorge da Silva Goncalves, Moritz Vandenhirtz, Alain Ryser, Irene Cannistraci, Julia E. Vogt
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
The paper introduces SALA, a plug‑in optimization framework that enables approximate machine unlearning methods to operate at the level of individual samples by aligning each example’s likelihood with its correct target distribution. It defines a sample‑grained distribution gap metric to quantify per‑sample discrepancies between approximate unlearning and exact retraining, and provides theoretical guarantees that SALA contracts this gap. Experiments on classification and generation tasks show that SALA can reduce the distribution gap by up to 86.67% and improve robustness to unlearning hyperparameters.
By Yaxin Xiao, Yulin Jin, Li Tang, Haoyang LI, Huadi Zheng, Qingqing Ye, Haibo Hu
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:2609.05966v1 Announce Type: new
Abstract: Existing unlearning approaches typically rely on post hoc weight adaptation or distillation, leading to duplicated memory costs, degraded generalizatio...
By Kushal Chakrabarti, Mayank Baranwal
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:2606. 03808v1 Announce Type: cross Abstract: We propose PURGE, a machine unlearning algorithm built on a simple but an under-exploited observation: continual learning (CL) and machine unlearning (MU) which are fundamentally dual problems.
By Vedant Jawandhia, Daksh Ahuja, Ghufran Alam Siddiqui, Prashant Trivedi, Yash Sinha, Pratik Narang
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:2605. 12765v3 Announce Type: replace Abstract: Large Language Models memorize vast amounts of training data, raising concerns regarding privacy, copyright infringement, and safety.
By Vin\'icius Conte Turani, Ot\'avio Parraga, Jo\~ao Vitor Boer Abitante, Kristen K. Arguello, Joana Pasquali, Ramiro N. Barros, Flavio du Pin Calmon, Christian Mattjie, Rodrigo C. Barros, Lucas S. Kupssinsk\"u
arXiv:2607. 06432v1 Announce Type: cross Abstract: Concept unlearning in text-to-image diffusion models is critical for safe and practical deployment: with rising privacy concerns, copyright disputes, trademark constraints, and safety regulations, deployed systems must be able to suppress unwanted concepts after training.
By Naveen George, Naoki Murata, Yuhta Takida, Konda Reddy Mopuri, Yuki Mitsufuji
arXiv:2604. 05634v2 Announce Type: replace Abstract: Machine unlearning (MU) has become a critical technique for GenAI models' safe and compliant operation.
By Zhiyong Ma, Zhitao Deng, Huan Tang, Jialin Chen, Zhijun Zheng, Zhengping Li, Qingyuan Chuai
arXiv:2606. 00105v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable progress on vision-language tasks, but they may also memorize and expose sensitive or restricted knowledge, raising concerns about privacy and broader safety risks.
By Junkai Chen, Yuhao He, Junxiang You, Ruiqi Liu, Chenyu Wang, Shu Wu