{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/machine-unlearning/papers/3","list_of":"/task/machine-unlearning","task":"Machine Unlearning","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":3,"pages_in_order":5,"rows_per_page":100,"rows":[201,300],"of":438,"counts":{"archive_papers_tagged":438,"with_a_code_link":173,"where_syntology_ran_a_sample":89,"not_listed_spam_title":0,"listed":438,"listed_where_code_ran":89,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":75,"every_run_a_failure_of_syntologys_instrument":14,"listed_with_a_run_with_no_instrument_failure":75,"listed_every_run_a_failure_of_syntologys_instrument":14,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/machine-unlearning","prev":"/task/machine-unlearning/papers/2","next":"/task/machine-unlearning/papers/4","papers":[{"url":null,"slug":"efficient-machine-unlearning-by-model","title":"Efficient Machine Unlearning by Model Splitting and Core Sample Selection","date":"2025-05-11","arxiv_id":"2505.07026","repositories_listed":0,"syntology":null},{"url":null,"slug":"unilogit-robust-machine-unlearning-for-llms","title":"Unilogit: Robust Machine Unlearning for LLMs Using Uniform-Target Self-Distillation","date":"2025-05-09","arxiv_id":"2505.06027","repositories_listed":0,"syntology":null},{"url":null,"slug":"obliviate-robust-and-practical-machine","title":"OBLIVIATE: Robust and Practical Machine Unlearning for Large Language Models","date":"2025-05-07","arxiv_id":"2505.04416","repositories_listed":0,"syntology":null},{"url":null,"slug":"memory-efficient-distributed-unlearning","title":"Memory-Efficient Distributed Unlearning","date":"2025-05-06","arxiv_id":"2505.03388","repositories_listed":0,"syntology":null},{"url":null,"slug":"erased-but-not-forgotten-how-backdoors","title":"Erased but Not Forgotten: How Backdoors Compromise Concept Erasure","date":"2025-04-29","arxiv_id":"2504.21072","repositories_listed":0,"syntology":null},{"url":null,"slug":"verifying-robust-unlearning-probing-residual","title":"Verifying Robust Unlearning: Probing Residual Knowledge in Unlearned Models","date":"2025-04-21","arxiv_id":"2504.14798","repositories_listed":0,"syntology":null},{"url":null,"slug":"fairness-and-robustness-in-machine-unlearning","title":"Fairness and Robustness in Machine Unlearning","date":"2025-04-18","arxiv_id":"2504.13610","repositories_listed":0,"syntology":null},{"url":null,"slug":"when-is-task-vector-provably-effective-for","title":"When is Task Vector Provably Effective for Model Editing? A Generalization Analysis of Nonlinear Transformers","date":"2025-04-15","arxiv_id":"2504.10957","repositories_listed":0,"syntology":null},{"url":null,"slug":"preserving-privacy-without-compromising","title":"Preserving Privacy Without Compromising Accuracy: Machine Unlearning for Handwritten Text Recognition","date":"2025-04-11","arxiv_id":"2504.08616","repositories_listed":0,"syntology":null},{"url":null,"slug":"saes-textit-can-improve-unlearning-dynamic","title":"SAEs $\\textit{Can}$ Improve Unlearning: Dynamic Sparse Autoencoder Guardrails for Precision Unlearning in LLMs","date":"2025-04-11","arxiv_id":"2504.08192","repositories_listed":0,"syntology":null},{"url":null,"slug":"sky-of-unlearning-soul-rewiring-federated","title":"Sky of Unlearning (SoUL): Rewiring Federated Machine Unlearning via Selective Pruning","date":"2025-04-02","arxiv_id":"2504.01705","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-federated-machine-unlearning","title":"Benchmarking Federated Machine Unlearning methods for Tabular Data","date":"2025-04-01","arxiv_id":"2504.00921","repositories_listed":0,"syntology":null},{"url":null,"slug":"prompting-forgetting-unlearning-in-gans-via","title":"Prompting Forgetting: Unlearning in GANs via Textual Guidance","date":"2025-04-01","arxiv_id":"2504.01218","repositories_listed":0,"syntology":null},{"url":null,"slug":"buyer-initiated-auction-mechanism-for-data","title":"Buyer-Initiated Auction Mechanism for Data Redemption in Machine Unlearning","date":"2025-03-29","arxiv_id":"2503.23001","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-verified-machine-unlearning-for","title":"Efficient Verified Machine Unlearning For Distillation","date":"2025-03-28","arxiv_id":"2503.22539","repositories_listed":0,"syntology":null},{"url":null,"slug":"frog-fair-removal-on-graphs","title":"FROG: Fair Removal on Graphs","date":"2025-03-23","arxiv_id":"2503.18197","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-contrastive-unlearning-for-language","title":"Deep Contrastive Unlearning for Language Models","date":"2025-03-19","arxiv_id":"2503.14900","repositories_listed":0,"syntology":null},{"url":null,"slug":"machine-unlearning-in-hyperbolic-vs-euclidean","title":"Machine Unlearning in Hyperbolic vs. Euclidean Multimodal Contrastive Learning: Adapting Alignment Calibration to MERU","date":"2025-03-19","arxiv_id":"2503.15166","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-machine-unlearning-for-quantized","title":"Robust Machine Unlearning for Quantized Neural Networks via Adaptive Gradient Reweighting with Similar Labels","date":"2025-03-18","arxiv_id":"2503.13917","repositories_listed":0,"syntology":null},{"url":null,"slug":"pebench-a-fictitious-dataset-to-benchmark","title":"PEBench: A Fictitious Dataset to Benchmark Machine Unlearning for Multimodal Large Language Models","date":"2025-03-16","arxiv_id":"2503.12545","repositories_listed":0,"syntology":null},{"url":null,"slug":"are-we-truly-forgetting-a-critical-re","title":"Are We Truly Forgetting? A Critical Re-examination of Machine Unlearning Evaluation Protocols","date":"2025-03-10","arxiv_id":"2503.06991","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-unlearn-while-retaining-combating","title":"Learning to Unlearn while Retaining: Combating Gradient Conflicts in Machine Unlearning","date":"2025-03-08","arxiv_id":"2503.06339","repositories_listed":0,"syntology":null},{"url":null,"slug":"node-level-contrastive-unlearning-on-graph","title":"Node-level Contrastive Unlearning on Graph Neural Networks","date":"2025-03-04","arxiv_id":"2503.02959","repositories_listed":0,"syntology":null},{"url":null,"slug":"amun-adversarial-machine-unlearning","title":"AMUN: Adversarial Machine UNlearning","date":"2025-03-02","arxiv_id":"2503.00917","repositories_listed":0,"syntology":null},{"url":null,"slug":"tape-tailored-posterior-difference-for","title":"TAPE: Tailored Posterior Difference for Auditing of Machine Unlearning","date":"2025-02-27","arxiv_id":"2502.19770","repositories_listed":0,"syntology":null},{"url":null,"slug":"holistic-audit-dataset-generation-for-llm","title":"Holistic Audit Dataset Generation for LLM Unlearning via Knowledge Graph Traversal and Redundancy Removal","date":"2025-02-26","arxiv_id":"2502.18810","repositories_listed":0,"syntology":null},{"url":null,"slug":"when-to-forget-complexity-trade-offs-in","title":"When to Forget? Complexity Trade-offs in Machine Unlearning","date":"2025-02-24","arxiv_id":"2502.17323","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-incremental-unlearning-techniques","title":"Exploring Incremental Unlearning: Techniques, Challenges, and Future Directions","date":"2025-02-23","arxiv_id":"2502.16708","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comprehensive-survey-of-machine-unlearning","title":"A Comprehensive Survey of Machine Unlearning Techniques for Large Language Models","date":"2025-02-22","arxiv_id":"2503.01854","repositories_listed":0,"syntology":null},{"url":null,"slug":"soft-token-attacks-cannot-reliably-audit","title":"Soft Token Attacks Cannot Reliably Audit Unlearning in Large Language Models","date":"2025-02-20","arxiv_id":"2502.15836","repositories_listed":0,"syntology":null},{"url":null,"slug":"safeeraser-enhancing-safety-in-multimodal","title":"SafeEraser: Enhancing Safety in Multimodal Large Language Models through Multimodal Machine Unlearning","date":"2025-02-18","arxiv_id":"2502.12520","repositories_listed":0,"syntology":null},{"url":null,"slug":"privacy-preservation-through-practical","title":"Privacy Preservation through Practical Machine Unlearning","date":"2025-02-15","arxiv_id":"2502.10635","repositories_listed":0,"syntology":null},{"url":null,"slug":"semu-singular-value-decomposition-for","title":"SEMU: Singular Value Decomposition for Efficient Machine Unlearning","date":"2025-02-11","arxiv_id":"2502.07587","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-sensitive-information-leakage-in","title":"Mitigating Sensitive Information Leakage in LLMs4Code through Machine Unlearning","date":"2025-02-09","arxiv_id":"2502.05739","repositories_listed":0,"syntology":null},{"url":null,"slug":"machine-unlearning-via-information-theoretic","title":"Machine Unlearning via Information Theoretic Regularization","date":"2025-02-08","arxiv_id":"2502.05684","repositories_listed":0,"syntology":null},{"url":null,"slug":"realistic-image-to-image-machine-unlearning","title":"Realistic Image-to-Image Machine Unlearning via Decoupling and Knowledge Retention","date":"2025-02-06","arxiv_id":"2502.04260","repositories_listed":0,"syntology":null},{"url":null,"slug":"falcon-fine-grained-activation-manipulation","title":"FALCON: Fine-grained Activation Manipulation by Contrastive Orthogonal Unalignment for Large Language Model","date":"2025-02-03","arxiv_id":"2502.01472","repositories_listed":0,"syntology":null},{"url":"/paper/redefining-machine-unlearning-a-conformal","slug":"redefining-machine-unlearning-a-conformal","title":"Redefining Machine Unlearning: A Conformal Prediction-Motivated Approach","date":"2025-01-31","arxiv_id":"2501.19403","repositories_listed":0,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/redefining-machine-unlearning-a-conformal#ran","syntology_url":"https://syntology.ai/paper/2501.19403","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.19403"}},"official":null}},{"url":null,"slug":"data-duplication-a-novel-multi-purpose-attack","title":"Data Duplication: A Novel Multi-Purpose Attack Paradigm in Machine Unlearning","date":"2025-01-28","arxiv_id":"2501.16663","repositories_listed":0,"syntology":null},{"url":null,"slug":"funu-boosting-machine-unlearning-efficiency","title":"FUNU: Boosting Machine Unlearning Efficiency by Filtering Unnecessary Unlearning","date":"2025-01-28","arxiv_id":"2501.16614","repositories_listed":0,"syntology":null},{"url":null,"slug":"toward-scalable-graph-unlearning-a-node","title":"Toward Scalable Graph Unlearning: A Node Influence Maximization based Approach","date":"2025-01-21","arxiv_id":"2501.11823","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-aligned-data-forgetting-via-twin","title":"Towards Aligned Data Forgetting via Twin Machine Unlearning","date":"2025-01-15","arxiv_id":"2501.08615","repositories_listed":0,"syntology":null},{"url":null,"slug":"open-problems-in-machine-unlearning-for-ai","title":"Open Problems in Machine Unlearning for AI Safety","date":"2025-01-09","arxiv_id":"2501.04952","repositories_listed":0,"syntology":null},{"url":null,"slug":"opengu-a-comprehensive-benchmark-for-graph","title":"OpenGU: A Comprehensive Benchmark for Graph Unlearning","date":"2025-01-06","arxiv_id":"2501.02728","repositories_listed":0,"syntology":null},{"url":null,"slug":"person-de-reidentification-a-variation-guided","title":"Person De-reidentification: A Variation-guided Identity Shift Modeling","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-illusion-of-unlearning-the-unstable","title":"The Illusion of Unlearning: The Unstable Nature of Machine Unlearning in Text-to-Image Diffusion Models","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-source-free-machine-unlearning","title":"Towards Source-Free Machine Unlearning","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comparative-study-of-machine-unlearning","title":"A Comparative Study of Machine Unlearning Techniques for Image and Text Classification Models","date":"2024-12-27","arxiv_id":"2412.19583","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-hybrid-framework-for-effective-and","title":"A hybrid framework for effective and efficient machine unlearning","date":"2024-12-19","arxiv_id":"2412.14505","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-recommendation-unlearning","title":"A Survey on Recommendation Unlearning: Fundamentals, Taxonomy, Evaluation, and Open Questions","date":"2024-12-17","arxiv_id":"2412.12836","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-utility-and-complexity-of-in-and-out-of","title":"The Utility and Complexity of in- and out-of-Distribution Machine Unlearning","date":"2024-12-12","arxiv_id":"2412.09119","repositories_listed":0,"syntology":null},{"url":null,"slug":"moderating-the-generalization-of-score-based","title":"Moderating the Generalization of Score-based Generative Model","date":"2024-12-10","arxiv_id":"2412.07229","repositories_listed":0,"syntology":null},{"url":null,"slug":"machine-unlearning-doesn-t-do-what-you-think","title":"Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy, Research, and Practice","date":"2024-12-09","arxiv_id":"2412.06966","repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-localized-machine-unlearning-through","title":"Improved Localized Machine Unlearning Through the Lens of Memorization","date":"2024-12-03","arxiv_id":"2412.02432","repositories_listed":0,"syntology":null},{"url":null,"slug":"learn-to-unlearn-meta-learning-based","title":"Learn to Unlearn: Meta-Learning-Based Knowledge Graph Embedding Unlearning","date":"2024-12-01","arxiv_id":"2412.00881","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-forget-using-hypernetworks","title":"Learning to Forget using Hypernetworks","date":"2024-12-01","arxiv_id":"2412.00761","repositories_listed":0,"syntology":null},{"url":null,"slug":"machine-unlearning-reveals-that-the-gender","title":"Machine Unlearning reveals that the Gender-based Violence Victim Condition can be detected from Speech in a Speaker-Agnostic Setting","date":"2024-11-27","arxiv_id":"2411.18177","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-machine-learning-to-machine-unlearning","title":"From Machine Learning to Machine Unlearning: Complying with GDPR's Right to be Forgotten while Maintaining Business Value of Predictive Models","date":"2024-11-26","arxiv_id":"2411.17126","repositories_listed":0,"syntology":null},{"url":null,"slug":"promoting-user-data-autonomy-during-the","title":"Promoting User Data Autonomy During the Dissolution of a Monopolistic Firm","date":"2024-11-20","arxiv_id":"2411.13546","repositories_listed":0,"syntology":null},{"url":null,"slug":"provable-unlearning-in-topic-modeling-and","title":"Provable unlearning in topic modeling and downstream tasks","date":"2024-11-19","arxiv_id":"2411.12600","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-review-on-machine-unlearning","title":"A Review on Machine Unlearning","date":"2024-11-18","arxiv_id":"2411.11315","repositories_listed":0,"syntology":null},{"url":null,"slug":"machine-unlearning-on-pre-trained-models-by","title":"Machine Unlearning on Pre-trained Models by Residual Feature Alignment Using LoRA","date":"2024-11-13","arxiv_id":"2411.08443","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-corrective-machine-unranking","title":"Neural Corrective Machine Unranking","date":"2024-11-13","arxiv_id":"2411.08562","repositories_listed":0,"syntology":null},{"url":null,"slug":"unlearning-in-vs-out-of-distribution-data-in","title":"Unlearning in- vs. out-of-distribution data in LLMs under gradient-based method","date":"2024-11-07","arxiv_id":"2411.04388","repositories_listed":0,"syntology":null},{"url":null,"slug":"game-theoretic-machine-unlearning-mitigating","title":"Game-Theoretic Machine Unlearning: Mitigating Extra Privacy Leakage","date":"2024-11-06","arxiv_id":"2411.03914","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-integrity-when-unlearning-with-t2i","title":"Model Integrity when Unlearning with T2I Diffusion Models","date":"2024-11-04","arxiv_id":"2411.02068","repositories_listed":0,"syntology":null},{"url":null,"slug":"pseudo-probability-unlearning-towards","title":"Pseudo-Probability Unlearning: Towards Efficient and Privacy-Preserving Machine Unlearning","date":"2024-11-04","arxiv_id":"2411.02622","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-class-unlearning-via-layer-wise","title":"Zero-shot Class Unlearning via Layer-wise Relevance Analysis and Neuronal Path Perturbation","date":"2024-10-31","arxiv_id":"2410.23693","repositories_listed":0,"syntology":null},{"url":null,"slug":"attribute-to-delete-machine-unlearning-via","title":"Attribute-to-Delete: Machine Unlearning via Datamodel Matching","date":"2024-10-30","arxiv_id":"2410.23232","repositories_listed":0,"syntology":null},{"url":null,"slug":"cliperase-efficient-unlearning-of-visual","title":"CLIPErase: Efficient Unlearning of Visual-Textual Associations in CLIP","date":"2024-10-30","arxiv_id":"2410.23330","repositories_listed":0,"syntology":null},{"url":null,"slug":"machine-unlearning-using-forgetting-neural","title":"Machine Unlearning using Forgetting Neural Networks","date":"2024-10-29","arxiv_id":"2410.22374","repositories_listed":0,"syntology":null},{"url":null,"slug":"unlearning-as-multi-task-optimization-a","title":"Unlearning as multi-task optimization: A normalized gradient difference approach with an adaptive learning rate","date":"2024-10-29","arxiv_id":"2410.22086","repositories_listed":0,"syntology":null},{"url":null,"slug":"when-machine-unlearning-meets-retrieval","title":"When Machine Unlearning Meets Retrieval-Augmented Generation (RAG): Keep Secret or Forget Knowledge?","date":"2024-10-20","arxiv_id":"2410.15267","repositories_listed":0,"syntology":null},{"url":null,"slug":"machine-unlearning-in-forgettability-sequence","title":"Machine Unlearning in Forgettability Sequence","date":"2024-10-09","arxiv_id":"2410.06446","repositories_listed":0,"syntology":null},{"url":null,"slug":"noise-is-all-you-need-private-second-order","title":"Noise is All You Need: Private Second-Order Convergence of Noisy SGD","date":"2024-10-09","arxiv_id":"2410.06878","repositories_listed":0,"syntology":null},{"url":null,"slug":"codeunlearn-amortized-zero-shot-machine","title":"CodeUnlearn: Amortized Zero-Shot Machine Unlearning in Language Models Using Discrete Concept","date":"2024-10-08","arxiv_id":"2410.10866","repositories_listed":0,"syntology":null},{"url":null,"slug":"why-fine-tuning-struggles-with-forgetting-in","title":"Why Fine-Tuning Struggles with Forgetting in Machine Unlearning? Theoretical Insights and a Remedial Approach","date":"2024-10-04","arxiv_id":"2410.03833","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-understanding-the-feasibility-of","title":"Towards Understanding the Feasibility of Machine Unlearning","date":"2024-10-03","arxiv_id":"2410.03043","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-unlearn-benchmarking-machine-unlearning","title":"Deep Unlearn: Benchmarking Machine Unlearning","date":"2024-10-02","arxiv_id":"2410.01276","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-backdoor-defense-in-multimodal","title":"Efficient Backdoor Defense in Multimodal Contrastive Learning: A Token-Level Unlearning Method for Mitigating Threats","date":"2024-09-29","arxiv_id":"2409.19526","repositories_listed":0,"syntology":null},{"url":null,"slug":"survey-of-security-and-data-attacks-on","title":"Survey of Security and Data Attacks on Machine Unlearning In Financial and E-Commerce","date":"2024-09-29","arxiv_id":"2410.00055","repositories_listed":0,"syntology":null},{"url":"/paper/score-forgetting-distillation-a-swift-data","slug":"score-forgetting-distillation-a-swift-data","title":"Score Forgetting Distillation: A Swift, Data-Free Method for Machine Unlearning in Diffusion Models","date":"2024-09-17","arxiv_id":"2409.11219","repositories_listed":0,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":6,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/score-forgetting-distillation-a-swift-data#ran","syntology_url":"https://syntology.ai/paper/2409.11219","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.11219"}},"official":null}},{"url":null,"slug":"enhancing-user-centric-privacy-protection-an","title":"Enhancing User-Centric Privacy Protection: An Interactive Framework through Diffusion Models and Machine Unlearning","date":"2024-09-05","arxiv_id":"2409.03326","repositories_listed":0,"syntology":null},{"url":null,"slug":"accurate-forgetting-for-all-in-one-image","title":"Accurate Forgetting for All-in-One Image Restoration Model","date":"2024-09-01","arxiv_id":"2409.00685","repositories_listed":0,"syntology":null},{"url":null,"slug":"forget-to-flourish-leveraging-machine","title":"Forget to Flourish: Leveraging Machine-Unlearning on Pretrained Language Models for Privacy Leakage","date":"2024-08-30","arxiv_id":"2408.17354","repositories_listed":0,"syntology":null},{"url":null,"slug":"unlearning-trojans-in-large-language-models-a","title":"Unlearning Trojans in Large Language Models: A Comparison Between Natural Language and Source Code","date":"2024-08-22","arxiv_id":"2408.12416","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-unified-framework-for-continual-learning","title":"A Unified Framework for Continual Learning and Unlearning","date":"2024-08-21","arxiv_id":"2408.11374","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-aligned-data-removal-via-twin-machine","title":"Towards Aligned Data Removal via Twin Machine Unlearning","date":"2024-08-21","arxiv_id":"2408.11433","repositories_listed":0,"syntology":null},{"url":null,"slug":"truvrf-towards-triple-granularity","title":"TruVRF: Towards Triple-Granularity Verification on Machine Unlearning","date":"2024-08-12","arxiv_id":"2408.06063","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-01689","title":"Controllable Unlearning for Image-to-Image Generative Models via $\\varepsilon$-Constrained Optimization","date":"2024-08-03","arxiv_id":"2408.01689","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-limitations-and-prospects-of-machine","title":"On the Limitations and Prospects of Machine Unlearning for Generative AI","date":"2024-08-01","arxiv_id":"2408.00376","repositories_listed":0,"syntology":null},{"url":null,"slug":"idea-a-flexible-framework-of-certified","title":"IDEA: A Flexible Framework of Certified Unlearning for Graph Neural Networks","date":"2024-07-28","arxiv_id":"2407.19398","repositories_listed":0,"syntology":null},{"url":null,"slug":"machine-unlearning-using-a-multi-gan-based","title":"Machine Unlearning using a Multi-GAN based Model","date":"2024-07-26","arxiv_id":"2407.18467","repositories_listed":0,"syntology":null},{"url":null,"slug":"learn-while-unlearn-an-iterative-unlearning","title":"Learn while Unlearn: An Iterative Unlearning Framework for Generative Language Models","date":"2024-07-25","arxiv_id":"2407.20271","repositories_listed":0,"syntology":null},{"url":null,"slug":"revisiting-machine-unlearning-with","title":"Revisiting Machine Unlearning with Dimensional Alignment","date":"2024-07-25","arxiv_id":"2407.17710","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-unlearn-for-robust-machine","title":"Learning to Unlearn for Robust Machine Unlearning","date":"2024-07-15","arxiv_id":"2407.10494","repositories_listed":0,"syntology":null},{"url":null,"slug":"faster-machine-unlearning-via-natural","title":"Faster Machine Unlearning via Natural Gradient Descent","date":"2024-07-11","arxiv_id":"2407.08169","repositories_listed":0,"syntology":null},{"url":null,"slug":"machine-unlearning-for-medical-imaging","title":"Machine Unlearning for Medical Imaging","date":"2024-07-10","arxiv_id":"2407.07539","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-backdoor-attacks-using-activation","title":"Mitigating Backdoor Attacks using Activation-Guided Model Editing","date":"2024-07-10","arxiv_id":"2407.07662","repositories_listed":0,"syntology":null},{"url":null,"slug":"releasing-malevolence-from-benevolence-the","title":"Releasing Malevolence from Benevolence: The Menace of Benign Data on Machine Unlearning","date":"2024-07-06","arxiv_id":"2407.05112","repositories_listed":0,"syntology":null}],"record_sha256":"455d23e85bb3501350f273743bed35519a634ee396a6135e7fdc4480570dceeb","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}