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
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
The paper introduces Dr. Post-Training, a framework that treats general training data as a data‑induced regularizer to prevent overfitting to scarce target objectives, rather than merely a pool for selection. It constructs a feasible set of model update directions from general data and projects target‑driven updates onto this set, unifying standard training and existing data‑selection methods as special cases along a bias‑variance spectrum. Experiments on SFT, RLHF, and RLVR demonstrate that these methods outperform both standard training and state‑of‑the‑art data‑selection baselines, especially when general and target data are highly misaligned, while system optimizations keep overhead minimal.
By Pingbang Hu, Xueshen Liu, Z. Morley Mao, Jiaqi W. Ma
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
INCONVENIENT is a new benchmark that evaluates how machine‑learning models, especially large language models, generalize when trained on convenience samples that bias feature–target relationships. Unlike prior distribution‑shift tests that rely on natural domain splits, INCONVENIENT explicitly perturbs these relationships while keeping the deployment population unchanged, allowing controlled study of shift severity and direction. The benchmark covers 200 tabular classification and regression datasets and produces about 15,500 shifted training distributions, revealing significant performance degradation.
By Sara Rezaeimanesh, Chad Klochko, Kundan Thind, Mohammad Ghassemi
arXiv:2605. 23595v2 Announce Type: replace-cross Abstract: The rapid advancement of machine learning has led to an unprecedented expansion of model ecosystems, making it increasingly difficult to assess the reliability of newly released models on unseen and unlabeled data.
By Trinh Pham, Viet Huynh, Hongzhi Yin, Quoc Viet Hung Nguyen, Thanh Tam Nguyen
arXiv:2606. 00399v1 Announce Type: new Abstract: Machine unlearning aims to remove the influence of specific training samples while preserving the model's utility.
By Rasa Khosrowshahli, Stephen Asobiela, Beatrice Ombuki-Berman, Shahryar Rahnamayan
arXiv:2607. 21353v1 Announce Type: new Abstract: Machine unlearning aims to remove the influence of specific training data while preserving model utility.
By Billel Habbati, Alessio Merlo, Luca Verderame, Meriem Guerar
arXiv:2609.38929v1 Announce Type: new
Abstract: Machine learning systems increasingly face the need to remove the influence of entire data domains, such as toxic language, harmful behavior, or topica...
By Pinaki Mohanty, Haoran Tang, Maggie Makar, Rajiv Khanna
Machine unlearning aims to remove the influence of specific training data while preserving model utility. Many state-of-the-art approaches pursue this goal by restricting the forgetting update to a subset of parameters selected through gradient-based saliency.
The paper compares five machine unlearning (MU) methods—NegGrad, Fine‑Tuning (FT), Random Labeling (RL), SalUn, and MUNBa—on noisy‑label correction across CIFAR‑10, CIFAR‑100, and Food‑101N. Results show that the best MU strategy depends on the noise type: FT works well for most closed‑set noise, RL and SalUn are robust and nearly match retraining accuracy under instance‑dependent noise, while MUNBa excels only under extreme symmetric noise. In open‑set noise, retraining on the cleaned data actually hurts performance, indicating that approximating retraining is not suitable in that regime, yet all MU methods still achieve near‑retraining accuracy on Food‑101N with much lower runtime.
By Jo\~ao L. P. Santana, Filipe R. Cordeiro
arXiv:2607. 11975v1 Announce Type: cross Abstract: Current machine unlearning methods predominantly rely on global, coarse-grained intervention strategies.
By Xujia Li, Dan Li, Jian Lou, Wenjie Feng