SOTAVerified

Machine Unlearning

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–50 of 438 papers

TitleStatusHype
MUSE: Machine Unlearning Six-Way Evaluation for Language ModelsCode4
SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse AutoencodersCode2
Protecting Privacy in Multimodal Large Language Models with MLLMU-BenchCode2
LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks YetCode2
Machine Unlearning in Generative AI: A SurveyCode2
RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language ModelsCode2
Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion ModelsCode2
Machine Unlearning of Pre-trained Large Language ModelsCode2
UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion ModelsCode2
Detecting Pretraining Data from Large Language ModelsCode2
Machine Unlearning: Solutions and ChallengesCode2
A Survey of Machine UnlearningCode2
Rectifying Privacy and Efficacy Measurements in Machine Unlearning: A New Inference Attack PerspectiveCode1
Membership Inference Attacks as Privacy Tools: Reliability, Disparity and EnsembleCode1
Unlearning Isn't Invisible: Detecting Unlearning Traces in LLMs from Model OutputsCode1
Certified Unlearning for Neural NetworksCode1
Rethinking Machine Unlearning in Image Generation ModelsCode1
Unlearning Isn't Deletion: Investigating Reversibility of Machine Unlearning in LLMsCode1
"Alexa, can you forget me?" Machine Unlearning Benchmark in Spoken Language UnderstandingCode1
A Survey on Unlearnable DataCode1
LoTUS: Large-Scale Machine Unlearning with a Taste of UncertaintyCode1
Safety Mirage: How Spurious Correlations Undermine VLM Safety Fine-tuningCode1
Data Unlearning in Diffusion ModelsCode1
Erasing Without Remembering: Implicit Knowledge Forgetting in Large Language ModelsCode1
MMUnlearner: Reformulating Multimodal Machine Unlearning in the Era of Multimodal Large Language ModelsCode1
Technical Report for the Forgotten-by-Design Project: Targeted Obfuscation for Machine LearningCode1
Benchmarking Vision Language Model Unlearning via Fictitious Facial Identity DatasetCode1
Identify Backdoored Model in Federated Learning via Individual UnlearningCode1
CLEAR: Character Unlearning in Textual and Visual ModalitiesCode1
Scalability of memorization-based machine unlearningCode1
Catastrophic Failure of LLM Unlearning via QuantizationCode1
Evaluating Deep Unlearning in Large Language ModelsCode1
A Closer Look at Machine Unlearning for Large Language ModelsCode1
NegMerge: Consensual Weight Negation for Strong Machine UnlearningCode1
Mitigating Memorization In Language ModelsCode1
Unified Gradient-Based Machine Unlearning with Remain Geometry EnhancementCode1
An Adversarial Perspective on Machine Unlearning for AI SafetyCode1
Alternate Preference Optimization for Unlearning Factual Knowledge in Large Language ModelsCode1
CURE4Rec: A Benchmark for Recommendation Unlearning with Deeper InfluenceCode1
Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMsCode1
Preserving Privacy in Large Language Models: A Survey on Current Threats and SolutionsCode1
Unlearning Targeted Information via Single Layer Unlearning GradientCode1
Learning to Refuse: Towards Mitigating Privacy Risks in LLMsCode1
On Large Language Model Continual UnlearningCode1
Composable Interventions for Language ModelsCode1
Soft Prompting for Unlearning in Large Language ModelsCode1
What makes unlearning hard and what to do about itCode1
Automatic Jailbreaking of the Text-to-Image Generative AI SystemsCode1
Machine Unlearning in Large Language ModelsCode1
Unlearning Concepts in Diffusion Model via Concept Domain Correction and Concept Preserving GradientCode1
Show:102550
← PrevPage 1 of 9Next →

No leaderboard results yet.