Machine Unlearning

Benchmarks archive 2025-07-28

No benchmark for this task in the archive.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

No dataset record in the archive lists this task.

Subtasks archive 2025-07-28

1 subtask in the archive's task tree.

Most implemented papers archive 2025-07-28

30 shown of 173 papers with code (438 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• MUSE: Machine Unlearning Six-Way Evaluation for Language Models
  8 Jul 2024 3 repositories listed
  Data owners may request the removal of their data from a trained model due to privacy or copyright concerns.
• Towards Adversarial Evaluations for Inexact Machine Unlearning
  17 Jan 2022 3 repositories listed
  Machine Learning models face increased concerns regarding the storage of personal user data and adverse impacts of corrupted data like backdoors or systematic bias.
• Machine Unlearning for Random Forests
  11 Sep 2020 3 repositories listed Syntology ran 8 of 8 samples · 0 unverified
  The upper levels of DaRE trees use random nodes, which choose split attributes and thresholds uniformly at random.
• RESTOR: Knowledge Recovery through Machine Unlearning
  31 Oct 2024 2 repositories listed Syntology ran 2 of 7 samples · 5 unverified · 2 pointer-only (licence)
  Large language models trained on web-scale corpora can memorize undesirable datapoints such as incorrect facts, copyrighted content or sensitive data.
• Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement
  29 Sep 2024 2 repositories listed Syntology ran 12 of 26 samples · 14 unverified · 3 pointer-only (licence)
  Approximate MU is a practical method for large-scale models.
• Opt-Out: Investigating Entity-Level Unlearning for Large Language Models via Optimal Transport
  18 Jun 2024 2 repositories listed Syntology ran 3 of 7 samples · 4 unverified
  Instruction-following large language models (LLMs), such as ChatGPT, have become widely popular among everyday users.
• Unlearning Concepts in Diffusion Model via Concept Domain Correction and Concept Preserving Gradient
  24 May 2024 2 repositories listed
  Text-to-image diffusion models have achieved remarkable success in generating photorealistic images.
• Certified Machine Unlearning via Noisy Stochastic Gradient Descent
  25 Mar 2024 2 repositories listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  ``The right to be forgotten'' ensured by laws for user data privacy becomes increasingly important.
• An Information Theoretic Approach to Machine Unlearning
  2 Feb 2024 2 repositories listed Syntology ran 14 of 15 samples · 1 unverified · 15 pointer-only (licence)
  We perform extensive empirical evaluation of our method over a range of contemporary benchmarks, verifying that our method is competitive with state-of-the-art performance under the strict constraints of zero-shot…
• Machine Unlearning for Image-to-Image Generative Models
  1 Feb 2024 2 repositories listed
  This paper serves as a bridge, addressing the gap by providing a unifying framework of machine unlearning for image-to-image generative models.
• Langevin Unlearning: A New Perspective of Noisy Gradient Descent for Machine Unlearning
  18 Jan 2024 2 repositories listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  Machine unlearning has raised significant interest with the adoption of laws ensuring the ``right to be forgotten''.
• MultiDelete for Multimodal Machine Unlearning
  18 Nov 2023 2 repositories listed Syntology ran 3 of 7 samples · 4 unverified · 7 pointer-only (licence)
  Machine Unlearning removes specific knowledge about training data samples from an already trained model.
• In-Context Unlearning: Language Models as Few Shot Unlearners
  11 Oct 2023 2 repositories listed Syntology ran 6 of 8 samples · 2 unverified · 8 pointer-only (licence)
  Machine unlearning, the study of efficiently removing the impact of specific training instances on a model, has garnered increased attention in recent years due to regulatory guidelines such as the \emph{Right to be…
• How to Combine Membership-Inference Attacks on Multiple Updated Models
  12 May 2022 2 repositories listed
  Our results on four public datasets show that our attacks are effective at using update information to give the adversary a significant advantage over attacks on standalone models, but also compared to a prior MI attack…
• Descent-to-Delete: Gradient-Based Methods for Machine Unlearning
  6 Jul 2020 2 repositories listed
  We study the data deletion problem for convex models.
• Machine Unlearning
  9 Dec 2019 2 repositories listed Syntology ran 1 of 4 samples · 3 unverified
  Once users have shared their data online, it is generally difficult for them to revoke access and ask for the data to be deleted.
• Model State Arithmetic for Machine Unlearning
  26 Jun 2025 1 repository listed Syntology ran 2 of 4 samples · 2 unverified
  Large language models are trained on massive corpora of web data, which may include private data, copyrighted material, factually inaccurate data, or data that degrades model performance.
• Membership Inference Attacks as Privacy Tools: Reliability, Disparity and Ensemble
  16 Jun 2025 1 repository listed
  Membership inference attacks (MIAs) pose a significant threat to the privacy of machine learning models and are widely used as tools for privacy assessment, auditing, and machine unlearning.
• Rectifying Privacy and Efficacy Measurements in Machine Unlearning: A New Inference Attack Perspective
  16 Jun 2025 1 repository listed
  In this work, we first identify several key pitfalls of the existing unlearning evaluation frameworks, e.
• Unlearning Isn't Invisible: Detecting Unlearning Traces in LLMs from Model Outputs
  16 Jun 2025 1 repository listed Syntology ran 0 of 7 samples · 7 unverified
  These traces can be identified from output responses, even when prompted with forget-irrelevant inputs.
• Apollo: A Posteriori Label-Only Membership Inference Attack Towards Machine Unlearning
  11 Jun 2025 1 repository listed
  Machine Unlearning (MU) aims to update Machine Learning (ML) models following requests to remove training samples and their influences on a trained model efficiently without retraining the original ML model from scratch.
• Certified Unlearning for Neural Networks
  8 Jun 2025 1 repository listed Syntology ran 0 of 1 samples · 1 unverified
  We address the problem of machine unlearning, where the goal is to remove the influence of specific training data from a model upon request, motivated by privacy concerns and regulatory requirements such as the "right…
• Towards Lifecycle Unlearning Commitment Management: Measuring Sample-level Unlearning Completeness
  6 Jun 2025 1 repository listed
  Growing concerns over data privacy and security highlight the importance of machine unlearning--removing specific data influences from trained models without full retraining.
• Rethinking Machine Unlearning in Image Generation Models
  3 Jun 2025 1 repository listed Syntology ran 1 of 1 samples · 0 unverified
  (2) We introduce EvalIGMU, a comprehensive evaluation framework.
• Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning
  2 Jun 2025 1 repository listed Syntology ran 3 of 6 samples · 3 unverified
  Machine unlearning offers a promising solution to privacy and safety concerns in large language models (LLMs) by selectively removing targeted knowledge while preserving utility.
• Aligned but Blind: Alignment Increases Implicit Bias by Reducing Awareness of Race
  30 May 2025 1 repository listed
  Although value-aligned language models (LMs) appear unbiased in explicit bias evaluations, they often exhibit stereotypes in implicit word association tasks, raising concerns about their fair usage.
• Unlearning Isn't Deletion: Investigating Reversibility of Machine Unlearning in LLMs
  22 May 2025 1 repository listed Syntology ran 0 of 4 samples · 4 unverified
  Unlearning in large language models (LLMs) is intended to remove the influence of specific data, yet current evaluations rely heavily on token-level metrics such as accuracy and perplexity.
• UniErase: Unlearning Token as a Universal Erasure Primitive for Language Models
  21 May 2025 1 repository listed
  Large language models require iterative updates to address challenges such as knowledge conflicts and outdated information (e.
• "Alexa, can you forget me?" Machine Unlearning Benchmark in Spoken Language Understanding
  21 May 2025 1 repository listed
  Machine unlearning, the process of efficiently removing specific information from machine learning models, is a growing area of interest for responsible AI.
• DUSK: Do Not Unlearn Shared Knowledge
  21 May 2025 1 repository listed
  When one set is designated for unlearning, an ideal method should remove its unique content while preserving shared facts.

Syntology lines on 16 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.