mlsanityData to 14 Oct 2026

DUCK: Distance-based Unlearning via Centroid Kinematics

arXiv 2312.02052 ↗First posted 4 Dec 2023cs.CV cs.LGcited by 13

On the map: LLM safety and security → Machine unlearning

Abstract (arXiv)

Machine Unlearning is rising as a new field, driven by the pressing necessity of ensuring privacy in modern artificial intelligence models. This technique primarily aims to eradicate any residual influence of a specific subset of data from the knowledge acquired by a neural model during its training. This work introduces a novel unlearning algorithm, denoted as Distance-based Unlearning via Centroid Kinematics (DUCK), which employs metric learning to guide the removal of samples matching the nearest incorrect centroid in the embedding space. Evaluation of the algorithm's performance is conducted across various benchmark datasets in two distinct scenarios, class removal, and homogeneous sampling removal, obtaining state-of-the-art performance. We also introduce a novel metric, called Adaptive Unlearning Score (AUS), encompassing not only the efficacy of the unlearning process in forgetting target data but also quantifying the performance loss relative to the original model. Additionally, we conducted a thorough investigation of the unlearning mechanism in DUCK, examining its impact on the organization of the feature space and employing explainable AI techniques for deeper insights.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Placed in Machine unlearning, one of 12 directions in LLM safety and security. Builds on 50 of its 68 references that are in the map. First posted on arXiv 4 Dec 2023.

Builds on

50 of 68 references.

Closest ancestors · 19

Same direction, newest first

  1. 2023MultiDelete for Multimodal Machine Unlearning18 Nov
  2. 2023Fast Machine Unlearning Without Retraining Through Selective Synaptic Dampening15 Aug
  3. 2023Machine Unlearning: Solutions and Challenges14 Aug
  4. 2023Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomy10 May
  5. 2023Model Sparsity Can Simplify Machine Unlearning11 Apr
  6. 2023Boundary Unlearning21 Mar
  7. 2023Towards Unbounded Machine Unlearning20 Feb
  8. 2022Deep Regression Unlearning15 Oct
  9. 2022A Survey of Machine Unlearning6 Sep
  10. 2022An Introduction to Machine Unlearning2 Sep
  11. 2022Adversarial Unlearning: Reducing Confidence Along Adversarial Directions3 Jun
  12. 2022Few-Shot Unlearning by Model Inversion31 May
7 more
  1. 2022Can Bad Teaching Induce Forgetting? Unlearning in Deep Networks using an Incompetent Teacher17 May
  2. 2022Deep Unlearning via Randomized Conditionally Independent Hessians15 Apr
  3. 2022Knowledge Removal in Sampling-based Bayesian Inference24 Mar
  4. 2022Zero-Shot Machine Unlearning14 Jan
  5. 2021Fast Yet Effective Machine Unlearning17 Nov
  6. 2021Hard to Forget: Poisoning Attacks on Certified Machine Unlearning17 Sep
  7. 2021Adaptive Machine Unlearning8 Jun

Other references · 31

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  3. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  4. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
  5. 2019Machine Unlearningcited by 1,061
  6. 2017VGGFace2: A dataset for recognising faces across pose and agecited by 914
  7. 2021Membership Inference Attacks From First Principlescited by 878
  8. 2019Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networkscited by 618
  9. 2019Certified Data Removal from Machine Learning Modelscited by 535
  10. 2018ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Modelscited by 498
  11. 2021Membership Inference Attacks on Machine Learning: A Surveycited by 321
  12. 2020Amnesiac Machine Learningcited by 319
19 more
  1. 2020Descent-to-Delete: Gradient-Based Methods for Machine Unlearningcited by 311
  2. 2020Systematic Evaluation of Privacy Risks of Machine Learning Modelscited by 292
  3. 2020When Machine Unlearning Jeopardizes Privacycited by 198
  4. 2020Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from Input-Output Observationscited by 180
  5. 2020DeltaGrad: Rapid retraining of machine learning modelscited by 149
  6. 2019Privacy Risks of Securing Machine Learning Models against Adversarial Examplescited by 141
  7. 2020Machine Unlearning for Random Forestscited by 131
  8. 2018Uncertainty in Neural Networks: Approximately Bayesian Ensemblingcited by 94
  9. 2022PUMA: Performance Unchanged Model Augmentation for Training Data Removalcited by 58
  10. 2020Towards Probabilistic Verification of Machine Unlearningcited by 50
  11. 2023GNNDelete: A General Strategy for Unlearning in Graph Neural Networkscited by 43
  12. 2022Unlearning Graph Classifiers with Limited Data Resourcescited by 31
  13. 2023Efficiently Forgetting What You Have Learned in Graph Representation Learning via Projectioncited by 20
  14. 2020Selective Forgetting of Deep Networks at a Finer Level than Samplescited by 13
  15. 2023Safe-CLIP: Removing NSFW Concepts from Vision-and-Language Modelscited by 12
  16. 2023Generative Adversarial Networks Unlearningcited by 11
  17. 2023Adapt then Unlearn: Exploring Parameter Space Semantics for Unlearning in Generative Adversarial Networkscited by 11
  18. 2020Class Clown: Data Redaction in Machine Unlearning at Enterprise Scalecited by 10
  19. 2023Learn, Unlearn and Relearn: An Online Learning Paradigm for Deep Neural Networkscited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 6; 2025: 3; 2026: 4.

13 papers.

Sort:

  1. 2024Are we making progress in unlearning? Findings from the first NeurIPS unlearning competitioncited by 50
  2. 2024Challenging Forgets: Unveiling the Worst-Case Forget Sets in Machine Unlearningcited by 44
  3. 2024Is Retain Set All You Need in Machine Unlearning? Restoring Performance of Unlearned Models with Out-Of-Distribution Imagescited by 18
  4. 2025Are We Truly Forgetting? A Critical Re-examination of Machine Unlearning Evaluation Protocolscited by 18
  5. 2024Remaining-data-free Machine Unlearning by Suppressing Sample Contributioncited by 13
  6. 2025Go Beyond Your Means: Unlearning with Per-Sample Gradient Orthogonalizationcited by 7
  7. 2025POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapsecited by 6
  8. 2026Erase at the Core: Representation Unlearning for Machine Unlearningcited by 5
  9. 2024ConDa: Fast Federated Unlearning with Contribution Dampeningcited by 2
  10. 2026Mitigating Privacy Risk via Forget Set-Free Unlearningcited by 2
  11. 2024Instance-Level Difficulty: A Missing Perspective in Machine Unlearningcited by 1
  12. 2026Jellyfish: Zero-Shot Federated Unlearning Scheme with Knowledge Disentanglementcited by 1
1 more
  1. 2026Erased, but Not Gone: Output Forgetting Is Not True Forgettingcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2025When to Forget? Complexity Trade-offs in Machine Unlearning
  2. 2026The BatchNorm Illusion: Diagnosing Normalization Artifacts in Machine Unlearning Evaluation
  3. 2024Machine Unlearning with Minimal Gradient Dependence for High Unlearning Ratios
  4. 2025LoTUS: Large-Scale Machine Unlearning with a Taste of Uncertainty
  5. 2026Easy Data Unlearning Bench
  6. 2024nabla τ: Gradient-based and Task-Agnostic machine Unlearning
  7. 2026Efficient Unlearning through Maximizing Relearning Convergence Delay
  8. 2025Exploring Nonlinear Pathway in Parameter Space for Machine Unlearning