SOTAVerified

Machine Unlearning

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 301–350 of 438 papers

TitleStatusHype
Privacy-Preserving Debiasing using Data Augmentation and Machine Unlearning—0
Promoting User Data Autonomy During the Dissolution of a Monopolistic Firm—0
Prompting Forgetting: Unlearning in GANs via Textual Guidance—0
Certified Minimax Unlearning with Generalization Rates and Deletion Capacity—0
Protecting Privacy Through Approximating Optimal Parameters for Sequence Unlearning in Language Models—0
Provable unlearning in topic modeling and downstream tasks—0
Pseudo-Probability Unlearning: Towards Efficient and Privacy-Preserving Machine Unlearning—0
Quantifying Cross-Modality Memorization in Vision-Language Models—0
Random Relabeling for Efficient Machine Unlearning—0
Realistic Image-to-Image Machine Unlearning via Decoupling and Knowledge Retention—0
Recalling The Forgotten Class Memberships: Unlearned Models Can Be Noisy Labelers to Leak Privacy—0
Buyer-Initiated Auction Mechanism for Data Redemption in Machine Unlearning—0
Reconstruction Attacks on Machine Unlearning: Simple Models are Vulnerable—0
Bounding Membership Inference—0
Redefining Machine Unlearning: A Conformal Prediction-Motivated Approach—0
Boundary Unlearning: Rapid Forgetting of Deep Networks via Shifting the Decision Boundary—0
Releasing Malevolence from Benevolence: The Menace of Benign Data on Machine Unlearning—0
Remembering Everything Makes You Vulnerable: A Limelight on Machine Unlearning for Personalized Healthcare Sector—0
Remember What You Want to Forget: Algorithms for Machine Unlearning—0
Update Selective Parameters: Federated Machine Unlearning Based on Model Explanation—0
Rethinking Machine Unlearning for Large Language Models—0
Boundary Unlearning—0
Accurate Forgetting for All-in-One Image Restoration Model—0
Revisiting Machine Unlearning with Dimensional Alignment—0
Verifiable Unlearning on Edge—0
Right to be Forgotten in the Era of Large Language Models: Implications, Challenges, and Solutions—0
RKLD: Reverse KL-Divergence-based Knowledge Distillation for Unlearning Personal Information in Large Language Models—0
Robust Machine Unlearning for Quantized Neural Networks via Adaptive Gradient Reweighting with Similar Labels—0
Benchmarking Federated Machine Unlearning methods for Tabular Data—0
SAEs Can Improve Unlearning: Dynamic Sparse Autoencoder Guardrails for Precision Unlearning in LLMs—0
PolicyCleanse: Backdoor Detection and Mitigation in Reinforcement Learning—0
SafeEraser: Enhancing Safety in Multimodal Large Language Models through Multimodal Machine Unlearning—0
SAFE: Machine Unlearning With Shard Graphs—0
Backdoor Defense with Machine Unlearning—0
SALAD: Systematic Assessment of Machine Unlearing on LLM-Aided Hardware Design—0
Exploiting Machine Unlearning for Backdoor Attacks in Deep Learning System—0
A Zest of LIME: Towards Architecture-Independent Model Distances—0
Zero-shot Class Unlearning via Layer-wise Relevance Analysis and Neuronal Path Perturbation—0
Score Forgetting Distillation: A Swift, Data-Free Method for Machine Unlearning in Diffusion Models—0
Ready2Unlearn: A Learning-Time Approach for Preparing Models with Future Unlearning Readiness—0
Second-Order Information Matters: Revisiting Machine Unlearning for Large Language Models—0
SecureCut: Federated Gradient Boosting Decision Trees with Efficient Machine Unlearning—0
Selective Forgetting: Advancing Machine Unlearning Techniques and Evaluation in Language Models—0
SEMU: Singular Value Decomposition for Efficient Machine Unlearning—0
Separable Multi-Concept Erasure from Diffusion Models—0
SEPS: A Separability Measure for Robust Unlearning in LLMs—0
A unified PAC-Bayesian framework for machine unlearning via information risk minimization—0
Verifying Robust Unlearning: Probing Residual Knowledge in Unlearned Models—0
Sharpness-Aware Machine Unlearning—0
Efficient Attribute Unlearning: Towards Selective Removal of Input Attributes from Feature Representations—0
Show:102550
← PrevPage 7 of 9Next →

No leaderboard results yet.