Papers with Code 아카이브

Machine Unlearning

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법전체 데이터셋

하위 태스크

1

평가표

0

보존된 평가 기록

0

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/chenchongthu/recommendation-unlearning

공식 코드

Recommendation Unlearning

https://github.com/chengjiali/Multimodal-Machine-Unlearning

공식 코드

MultiDelete for Multimodal Machine Unlearning

https://github.com/childeden/ispf

공식 코드

Toward Efficient Data-Free Unlearning

https://github.com/claserken/SISS

공식 코드

Data Unlearning in Diffusion Models

https://github.com/cleverhans-lab/machine-unlearning

공식 코드

Machine Unlearning

https://github.com/cleverhans-lab/unrolling-sgd

공식 코드

Unrolling SGD: Understanding Factors Influencing Machine Unlearning

https://github.com/cleverhans-lab/verifiable-unlearning

공식 코드

Verifiable and Provably Secure Machine Unlearning

https://github.com/clu-uml/mu-bench

공식 코드

MU-Bench: A Multitask Multimodal Benchmark for Machine Unlearning

https://github.com/clu-uml/multidelete

공식 코드

MultiDelete for Multimodal Machine Unlearning

https://github.com/cp-lab-uts/reinforcement-unlearning

공식 코드

Reinforcement Unlearning

https://github.com/csm9493/efficient-llm-unlearning

공식 코드

Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMs

https://github.com/cspartalis/lotus

공식 코드

LoTUS: Large-Scale Machine Unlearning with a Taste of Uncertainty

https://github.com/cywinski/saeuron

공식 코드

SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders

https://github.com/datasec-lab/ruli

공식 코드

Rectifying Privacy and Efficacy Measurements in Machine Unlearning: A New Inference Attack Perspective

https://github.com/drimpossible/corrective-unlearning-bench

공식 코드

Corrective Machine Unlearning

https://github.com/ethz-spylab/Blind-MIA

공식 코드

Blind Baselines Beat Membership Inference Attacks for Foundation Models

https://github.com/ethz-spylab/unlearning-vs-safety

공식 코드

An Adversarial Perspective on Machine Unlearning for AI Safety

https://github.com/exploration-lab/relu

공식 코드

Towards Robust Evaluation of Unlearning in LLMs via Data Transformations

https://github.com/franciscoliu/MLLMU-Bench

공식 코드

Protecting Privacy in Multimodal Large Language Models with MLLMU-Bench

https://github.com/franciscoliu/genai-mu-reading

공식 코드

Machine Unlearning in Generative AI: A Survey

https://github.com/franciscoliu/sku

공식 코드

Towards Safer Large Language Models through Machine Unlearning

https://github.com/fshp971/mcmc-unlearning

공식 코드

Knowledge Removal in Sampling-based Bayesian Inference

https://github.com/gcyzsl/o3-llm-unlearning

공식 코드

On Large Language Model Continual Unlearning

https://github.com/graph-com/langevin_unlearning

공식 코드

Langevin Unlearning: A New Perspective of Noisy Gradient Descent for Machine Unlearning

https://github.com/graph-com/sgd_unlearning

공식 코드

Certified Machine Unlearning via Noisy Stochastic Gradient Descent

https://github.com/guangyaodou/SSU_Unlearn

공식 코드

Avoiding Copyright Infringement via Large Language Model Unlearning

https://github.com/guangyaodou/conmu

공식 코드

Breaking the Trilemma of Privacy, Utility, Efficiency via Controllable Machine Unlearning

https://github.com/happy2git/guide

공식 코드

Inductive Graph Unlearning

https://github.com/happy2git/unlearning_inference_iam

공식 코드

Towards Lifecycle Unlearning Commitment Management: Measuring Sample-level Unlearning Completeness

https://github.com/hartvigsen-group/composable-interventions

공식 코드

Composable Interventions for Language Models

https://github.com/hnanhtuan/projected_gradient_unlearning

공식 코드

Learn to Unlearn for Deep Neural Networks: Minimizing Unlearning Interference with Gradient Projection

https://github.com/hqc-ml/machine-unlearning-via-null-space-calibration

공식 코드

Machine Unlearning via Null Space Calibration

https://github.com/if-loops/selective-synaptic-dampening

공식 코드

Fast Machine Unlearning Without Retraining Through Selective Synaptic Dampening

https://github.com/if-loops/towards_poison_unlearning

공식 코드

Potion: Towards Poison Unlearning

https://github.com/inspire-group/unlearning-verification

공식 코드

Towards Probabilistic Verification of Machine Unlearning

https://github.com/jbonato1/scar

공식 코드

Is Retain Set All You Need in Machine Unlearning? Restoring Performance of Unlearned Models with Out-Of-Distribution Images

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.