Pith. sign in

REVIEW 24 cited by

A Survey of Machine Unlearning

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2209.02299 v6 pith:7ZBFXPNO submitted 2022-09-06 cs.LG cs.AI

A Survey of Machine Unlearning

classification cs.LG cs.AI
keywords machinedataunlearningmodelsapplicationscomprehensivecomputerprivacy
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Today, computer systems hold large amounts of personal data. Yet while such an abundance of data allows breakthroughs in artificial intelligence, and especially machine learning (ML), its existence can be a threat to user privacy, and it can weaken the bonds of trust between humans and AI. Recent regulations now require that, on request, private information about a user must be removed from both computer systems and from ML models, i.e. ``the right to be forgotten''). While removing data from back-end databases should be straightforward, it is not sufficient in the AI context as ML models often `remember' the old data. Contemporary adversarial attacks on trained models have proven that we can learn whether an instance or an attribute belonged to the training data. This phenomenon calls for a new paradigm, namely machine unlearning, to make ML models forget about particular data. It turns out that recent works on machine unlearning have not been able to completely solve the problem due to the lack of common frameworks and resources. Therefore, this paper aspires to present a comprehensive examination of machine unlearning's concepts, scenarios, methods, and applications. Specifically, as a category collection of cutting-edge studies, the intention behind this article is to serve as a comprehensive resource for researchers and practitioners seeking an introduction to machine unlearning and its formulations, design criteria, removal requests, algorithms, and applications. In addition, we aim to highlight the key findings, current trends, and new research areas that have not yet featured the use of machine unlearning but could benefit greatly from it. We hope this survey serves as a valuable resource for ML researchers and those seeking to innovate privacy technologies. Our resources are publicly available at https://github.com/tamlhp/awesome-machine-unlearning.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 24 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. The Measure of Deception: An Analysis of Data Forging in Machine Unlearning

    cs.LG 2025-09 conditional novelty 8.0

    The Lebesgue measure of ε-forging sets decays as O(ε) or ε^d for linear models and as ε^{(d-r)/2} under mild regularity assumptions, with vanishing probability of random sampling.

  2. Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning

    cs.LG 2024-04 conditional novelty 8.0

    NPO enables stable unlearning of 50%+ training data in LLMs on TOFU by making collapse exponentially slower than gradient ascent, preserving sensible outputs where prior methods fail.

  3. Inducing Artificial Uncertainty in Language Models

    cs.CL 2026-05 unverdicted novelty 7.0

    Inducing artificial uncertainty on trivial tasks allows training probes that achieve higher calibration on hard data than standard approaches while retaining performance on easy data.

  4. Revisiting Privacy Leakage in Machine Unlearning: Membership Inference Beyond the Forgotten Set

    cs.CR 2026-05 unverdicted novelty 7.0

    TC-UMIA is a population-level attack using pre- and post-unlearning predictions to infer membership across forget, retain, and unseen sets, revealing added privacy leakage to retained data.

  5. Revisiting Privacy Leakage in Machine Unlearning: Membership Inference Beyond the Forgotten Set

    cs.CR 2026-05 unverdicted novelty 7.0

    Unlearning increases privacy leakage for the retain set, and a new tri-class membership inference attack distinguishes forget, retain, and unseen data using pre- and post-unlearning model outputs.

  6. Efficient Unlearning through Maximizing Relearning Convergence Delay

    cs.LG 2026-04 unverdicted novelty 7.0

    The Influence Eliminating Unlearning framework maximizes relearning convergence delay via weight decay and noise injection to remove the influence of a forgetting set while preserving accuracy on retained data.

  7. Is your algorithm unlearning or untraining?

    cs.LG 2026-04 conditional novelty 7.0

    Machine unlearning conflates reversing the influence of specific training examples (untraining) with removing the full underlying distribution or behavior (unlearning).

  8. Improving LLM Unlearning Robustness via Random Perturbations

    cs.CL 2025-01 unverdicted novelty 7.0

    LLM unlearning is reframed as inadvertently installing backdoor triggers on forget-tokens; Random Noise Augmentation is introduced as a defense that improves robustness with theoretical guarantees.

  9. POPS: Recovering Unlearned Multi-Modality Knowledge in MLLMs with Prompt-Optimized Parameter Shaking

    cs.CR 2026-07 conditional novelty 6.0

    Prompt-optimized suffixes plus synthetic fine-tuning recover ~82% of knowledge that multimodal unlearning methods claim to erase from MLLMs.

  10. Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces

    cs.LG 2026-05 unverdicted novelty 6.0

    A latent mediation framework with sparse autoencoders enables non-additive token-level influence attribution in LLMs by learning orthogonal features and back-propagating attributions.

  11. LLM Ghostbusters: Surgical Hallucination Suppression via Adaptive Unlearning

    cs.CR 2026-05 unverdicted novelty 6.0

    Adaptive Unlearning suppresses package hallucinations in code-generating LLMs by 81% while preserving benchmark performance, using model-generated data and no human labels.

  12. Unlearning What Matters: Token-Level Attribution for Precise Language Model Unlearning

    cs.CL 2026-05 unverdicted novelty 6.0

    TokenUnlearn identifies critical tokens via masking and entropy signals then applies hard selection or soft weighting to unlearn only those tokens, yielding better forgetting and retained utility than sequence-level b...

  13. Representation-Guided Parameter-Efficient LLM Unlearning

    cs.CL 2026-04 unverdicted novelty 6.0

    REGLU guides LoRA-based unlearning via representation subspaces and orthogonal regularization to outperform prior methods on forget-retain trade-off in LLM benchmarks.

  14. Forget-It-All: Multi-Concept Machine Unlearning via Concept-Aware Neuron Masking

    cs.CV 2026-01 unverdicted novelty 6.0

    FIA uses contrastive concept saliency and temporal-spatial neuron identification to build unified masks that erase multiple target concepts while preserving general generation quality in diffusion models.

  15. A Common Pool of Privacy Problems: Legal and Technical Lessons from a Large-Scale Web-Scraped Machine Learning Dataset

    cs.CR 2025-06 unverdicted novelty 6.0

    An empirical audit of one web-scraped ML training dataset reveals persistent PII after sanitization, which the authors combine with legal analysis to highlight privacy risks and advocate redefining 'publicly available...

  16. Towards Reliable Forgetting: A Survey on Machine Unlearning Verification

    cs.LG 2025-06 unverdicted novelty 6.0

    A survey that organizes machine unlearning verification methods into behavioral and parametric categories and outlines open problems.

  17. Verification of Machine Unlearning is Fragile

    cs.LG 2024-08 unverdicted novelty 6.0

    Verification of machine unlearning is fragile because model providers can use adversarial unlearning to pass checks while keeping data influence.

  18. SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation

    cs.LG 2023-10 conditional novelty 6.0

    SalUn uses gradient-based weight saliency to achieve effective machine unlearning of data, classes, or concepts in image classification and generation, narrowing the gap to exact retraining.

  19. Cognitive Architectures for Language Agents

    cs.AI 2023-09 accept novelty 6.0

    CoALA is a modular cognitive architecture for language agents that organizes memory components, action spaces for internal and external interaction, and a generalized decision-making loop to support more systematic de...

  20. Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks

    cs.LG 2026-07 conditional novelty 5.0

    A system-first taxonomy and literature synthesis of multimodal unlearning across vision, language, video, and audio, with datasets, benchmarks, metrics, applications, and open challenges.

  21. Exact Unlearning from Proxies Induces Closeness Guarantees on Approximate Unlearning

    cs.LG 2026-05 unverdicted novelty 5.0

    Inferring data distributions precisely allows distilling exact unlearning signals, yielding KL divergence bounds to the retrained model and outperforming competitors in three forgetting scenarios.

  22. Machine Unlearning on Pre-trained Models by Residual Feature Alignment Using LoRA

    cs.LG 2024-11 unverdicted novelty 5.0

    A LoRA-based residual feature alignment method for efficient machine unlearning on pre-trained models by targeting zero residuals on retained data and shifted residuals on unlearned data.

  23. Towards Certified Unlearning for Deep Neural Networks

    cs.LG 2024-08 unverdicted novelty 5.0

    Proposes simple techniques and inverse Hessian approximation to enable certified unlearning for nonconvex DNN objectives, including nonconvergent training and sequential unlearning requests.

  24. Machine Unlearning: A Comprehensive Survey

    cs.CR 2024-05 unverdicted novelty 2.0

    A survey classifying machine unlearning into centralized (exact and approximate), distributed/irregular data, verification, and privacy/security categories with technique overviews.