SOTAVerified

Machine Unlearning

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 201–250 of 438 papers

TitleStatusHype
Learning to Forget using Hypernetworks—0
Machine Unlearning reveals that the Gender-based Violence Victim Condition can be detected from Speech in a Speaker-Agnostic Setting—0
From Machine Learning to Machine Unlearning: Complying with GDPR's Right to be Forgotten while Maintaining Business Value of Predictive Models—0
MUNBa: Machine Unlearning via Nash BargainingCode0
Towards Robust Evaluation of Unlearning in LLMs via Data TransformationsCode0
Verifying Machine Unlearning with Explainable AICode0
Promoting User Data Autonomy During the Dissolution of a Monopolistic Firm—0
Provable unlearning in topic modeling and downstream tasks—0
A Review on Machine Unlearning—0
LoRA Unlearns More and Retains More (Student Abstract)Code0
Machine Unlearning on Pre-trained Models by Residual Feature Alignment Using LoRA—0
Neural Corrective Machine Unranking—0
Unlearning in- vs. out-of-distribution data in LLMs under gradient-based method—0
Game-Theoretic Machine Unlearning: Mitigating Extra Privacy Leakage—0
Model Integrity when Unlearning with T2I Diffusion Models—0
Pseudo-Probability Unlearning: Towards Efficient and Privacy-Preserving Machine Unlearning—0
Zero-shot Class Unlearning via Layer-wise Relevance Analysis and Neuronal Path Perturbation—0
RESTOR: Knowledge Recovery through Machine UnlearningCode0
Attribute-to-Delete: Machine Unlearning via Datamodel Matching—0
CLIPErase: Efficient Unlearning of Visual-Textual Associations in CLIP—0
Unlearning as multi-task optimization: A normalized gradient difference approach with an adaptive learning rate—0
Machine Unlearning using Forgetting Neural Networks—0
When Machine Unlearning Meets Retrieval-Augmented Generation (RAG): Keep Secret or Forget Knowledge?—0
Edge Unlearning is Not "on Edge"! An Adaptive Exact Unlearning System on Resource-Constrained DevicesCode0
Efficient Federated Unlearning under Plausible DeniabilityCode0
MUSO: Achieving Exact Machine Unlearning in Over-Parameterized RegimesCode0
Machine Unlearning in Forgettability Sequence—0
Noise is All You Need: Private Second-Order Convergence of Noisy SGD—0
CodeUnlearn: Amortized Zero-Shot Machine Unlearning in Language Models Using Discrete Concept—0
Why Fine-Tuning Struggles with Forgetting in Machine Unlearning? Theoretical Insights and a Remedial Approach—0
Towards Understanding the Feasibility of Machine Unlearning—0
DynFrs: An Efficient Framework for Machine Unlearning in Random ForestCode0
Deep Unlearn: Benchmarking Machine Unlearning—0
Survey of Security and Data Attacks on Machine Unlearning In Financial and E-Commerce—0
Efficient Backdoor Defense in Multimodal Contrastive Learning: A Token-Level Unlearning Method for Mitigating Threats—0
Distribution-Level Feature Distancing for Machine Unlearning: Towards a Better Trade-off Between Model Utility and ForgettingCode0
Score Forgetting Distillation: A Swift, Data-Free Method for Machine Unlearning in Diffusion Models—0
Rewind-to-Delete: Certified Machine Unlearning for Nonconvex FunctionsCode0
Enhancing User-Centric Privacy Protection: An Interactive Framework through Diffusion Models and Machine Unlearning—0
Accurate Forgetting for All-in-One Image Restoration Model—0
Forget to Flourish: Leveraging Machine-Unlearning on Pretrained Language Models for Privacy Leakage—0
Unlearning Trojans in Large Language Models: A Comparison Between Natural Language and Source Code—0
A Unified Framework for Continual Learning and Unlearning—0
Towards Aligned Data Removal via Twin Machine Unlearning—0
TruVRF: Towards Triple-Granularity Verification on Machine Unlearning—0
Neural Machine UnrankingCode0
Controllable Unlearning for Image-to-Image Generative Models via -Constrained Optimization—0
Verification of Machine Unlearning is FragileCode0
On the Limitations and Prospects of Machine Unlearning for Generative AI—0
Towards Certified Unlearning for Deep Neural NetworksCode0
Show:102550
← PrevPage 5 of 9Next →

No leaderboard results yet.