SOTAVerified

Machine Unlearning

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 151–175 of 438 papers

TitleStatusHype
Learn while Unlearn: An Iterative Unlearning Framework for Generative Language Models—0
Leveraging Per-Instance Privacy for Machine Unlearning—0
AMUN: Adversarial Machine UNlearning—0
Deep Unlearn: Benchmarking Machine Unlearning—0
Learn to Forget: Machine Unlearning via Neuron Masking—0
IDEA: A Flexible Framework of Certified Unlearning for Graph Neural Networks—0
DeepObliviate: A Powerful Charm for Erasing Data Residual Memory in Deep Neural Networks—0
PolicyCleanse: Backdoor Detection and Mitigation in Reinforcement Learning—0
Learn to Unlearn: A Survey on Machine Unlearning—0
Heterogeneous Decentralized Machine Unlearning with Seed Model Distillation—0
Deep Contrastive Unlearning for Language Models—0
Towards Lifecycle Unlearning Commitment Management: Measuring Sample-level Approximate Unlearning Completeness—0
DeepClean: Machine Unlearning on the Cheap by Resetting Privacy Sensitive Weights using the Fisher Diagonal—0
Backdoor Defense with Machine Unlearning—0
Decoupling the Class Label and the Target Concept in Machine Unlearning—0
Exploiting Machine Unlearning for Backdoor Attacks in Deep Learning System—0
Holistic Audit Dataset Generation for LLM Unlearning via Knowledge Graph Traversal and Redundancy Removal—0
GraphMU: Repairing Robustness of Graph Neural Networks via Machine Unlearning—0
Gradient Surgery for One-shot Unlearning on Generative Model—0
Deciphering the Impact of Pretraining Data on Large Language Models through Machine Unlearning—0
Improved Localized Machine Unlearning Through the Lens of Memorization—0
A More Practical Approach to Machine Unlearning—0
A Comparative Study of Machine Unlearning Techniques for Image and Text Classification Models—0
Benchmarking Federated Machine Unlearning methods for Tabular Data—0
Learn to Unlearn: Meta-Learning-Based Knowledge Graph Embedding Unlearning—0
Show:102550
← PrevPage 7 of 18Next →

No leaderboard results yet.