mlsanityData to 14 Oct 2026

Similarity-Aware Machine Unlearning

arXiv 2608.00246 ↗First posted 31 Jul 2026cs.LGcited by 0

On the map: LLM safety and security → Machine unlearning

Abstract (arXiv)

Machine unlearning removes the influence of user-specified training examples from a trained model, avoiding the need to retrain it from scratch. Localization-based methods improve unlearning efficiency by identifying a subset of influential model parameters. However, existing approaches select parameters based solely on forget-set importance, neglecting their role in retained dataset and often causing collateral damage to semantically similar retained examples. We address this limitation with a retain-aware localization method that considers parameter importance to both forgotten and retained data. We also introduce a retain-similar evaluation set, constructed using cosine similarity in the model embedding space, to directly measure collateral damage. Across eleven experimental settings on CIFAR-10 dataset and ResNet18 model, our method consistently reduces collateral damage while improving standard unlearning metrics, demonstrating the effectiveness of retain-aware localization for similarity-aware machine unlearning.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Machine unlearning, one of 12 directions in LLM safety and security. Builds on 16 of its 25 references that are in the map. First posted on arXiv 31 Jul 2026.

Builds on

16 of 25 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024Improved Localized Machine Unlearning Through the Lens of Memorization3 Dec
  2. 2023SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation19 Oct
  3. 2023Machine Unlearning: Solutions and Challenges14 Aug
  4. 2022A Survey of Machine Unlearning6 Sep

Other references · 12

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  3. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  4. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,611
  5. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
  6. 2020Extracting Training Data from Large Language Modelscited by 2,189
  7. 2019Machine Unlearningcited by 1,061
  8. 2019Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networkscited by 618
  9. 2020What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimationcited by 497
  10. 2019Does Learning Require Memorization? A Short Tale about a Long Tailcited by 460
  11. 2020Variational Bayesian Unlearningcited by 117
  12. 2024Memorization in deep learning: A surveycited by 15

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Are We Truly Forgetting? A Critical Re-examination of Machine Unlearning Evaluation Protocols
  2. 2026Forgetting Has Neighbors: Localized Collateral Forgetting in Machine Unlearning
  3. 2026Forgetting Similar Samples: Can Machine Unlearning Do it Better?
  4. 2026Erase at the Core: Representation Unlearning for Machine Unlearning
  5. 2025CoUn: Empowering Machine Unlearning via Contrastive Learning
  6. 2025Learning to Unlearn while Retaining: Combating Gradient Conflicts in Machine Unlearning
  7. 2026The BatchNorm Illusion: Diagnosing Normalization Artifacts in Machine Unlearning Evaluation
  8. 2025Unlearning Isn't Deletion: Investigating Reversibility of Machine Unlearning in LLMs