unlearning

There are 1 repository under unlearning topic.

zjunlp / EasyEdit
An Easy-to-use Knowledge Editing Framework for LLMs.
artificial-intelligence baichuan chatgpt easyedit efficient gpt knowledge-editing knowlm large-language-models llama llama2 mistral mmedit model-editing natural-language-processing open-source-project safeedit tool trustworthy-ai unlearning
Language:Jupyter Notebook 1439
tamlhp / awesome-machine-unlearning
Awesome Machine Unlearning (A Survey of Machine Unlearning)
continual-learning data-deletion data-privacy data-removal forgetting machine-unlearning unlearning federated-unlearning few-shot-unlearning model-certification recommendation-unlearning unlearning-verification membership-inference deep-unlearning feature-injection right-to-be-forgotten gdpr llm-unlearning
Language:Jupyter Notebook 610
OPTML-Group / Unlearn-Saliency
[ICLR24 (Spotlight)] "SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation" by Chongyu Fan*, Jiancheng Liu*, Yihua Zhang, Eric Wong, Dennis Wei, Sijia Liu
unlearning machine-unlearning data-removal diffusion diffusion-models forgetting generative-model data-deletion data-privacy membership-inference membership-inference-attack
Language:Python 73
OPTML-Group / Unlearn-Sparse
[NeurIPS23 (Spotlight)] "Model Sparsity Can Simplify Machine Unlearning" by Jinghan Jia*, Jiancheng Liu*, Parikshit Ram, Yuguang Yao, Gaowen Liu, Yang Liu, Pranay Sharma, Sijia Liu
data-privacy machine-unlearning data-deletion data-removal forgetting membership-inference membership-inference-attack unlearning
Language:Python 52
OPTML-Group / Diffusion-MU-Attack
The official implementation of the paper "To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsafe Images ... For Now". This work introduces one fast and effective attack method to evaluate the harmful-content generation ability of safety-driven unlearned diffusion models.
attack-unlearned-diffusion-model stable-diffusion unlearning adversarial-attacks evaluation-framework robustness
Language:Python 29
nkdinsdale / Unlearning_for_MRI_harmonisation
Code for implementation of Unlearning Scanner Bias for MRI Harmonisation
domain-adaptation harmonisation unlearning
Language:Python 25
bjzhb666 / GS-LoRA
Continual Forgetting for Pre-trained Vision Models (CVPR 2024)
casia-webface continual-forgetting continual-learning editing face-transformer forgetting machine-unlearning model-editing unlearning
Language:Python 20
KID-22 / LLM-Unlearning-Survey
chatgpt llm machine-unlearning unlearning llm-unlearning
20
chrisliu298 / awesome-llm-unlearning
A resource repository for machine unlearning in large language models
awesome llm llm-unlearning unlearning machine-unlearning alignment large-language-model
17
fmy266 / Pytorch-Backdoor-Unlearning
Pytorch implementation of backdoor unlearning.
backdoor unlearning defense
Language:Python 14
pbevan1 / Detecting-Melanoma-Fairly
Implementation for MICCAI DART paper: 'Detecting Melanoma Fairly: Skin Tone Detection and Debiasing for Skin Lesion Classification'
cnn deep-learning convolutional-neural-networks debiasing dermatology domain-adaptation melanoma-classification melanoma-detection unlearning confusion-loss debiasing-neural-networks gradient-reversal gradient-reversal-layer learning-not-to-learn pytorch turning-a-blind-eye vae variational-autoencoder db-vae skin-tone-detection
Language:Python 14
OPTML-Group / Unlearn-WorstCase
"Challenging Forgets: Unveiling the Worst-Case Forget Sets in Machine Unlearning" by Chongyu Fan*, Jiancheng Liu*, Alfred Hero, Sijia Liu
data-deletion data-privacy data-removal evaluation forgetting machine-unlearning unlearning evaluation-framework
Language:Python 7
vicw0ng-hk / feul
Repo on unlearning in FL. FYP22002@HKUCS.
federated-learning final-year-project notebook unlearning
Language:Jupyter Notebook 6
hslyu / GIF
Official implementation of "Deeper Understanding of Black-box Predictions via Generalized Influence Functions".
influence-functions machine-learning unlearning
Language:Jupyter Notebook 5
pbevan1 / Skin-Deep-Unlearning
Implementation for ICML 2022 paper: 'Skin Deep Unlearning: Artefact and Instrument Debiasing in the Context of Melanoma Classification'
deep-learning convolutional-neural-networks cnn melanoma-detection melanoma-classification debiasing debiasing-neural-networks learning-not-to-learn turning-a-blind-eye unlearning dermatology domain-adaptation domain-generalization gradient-reversal gradient-reversal-layer confusion-loss icml icml-2022
Language:Python 5
awesome-machine-unlearning / awesome-machine-unlearning.github.io
Official Website of https://github.com/tamlhp/awesome-machine-unlearning
machine-unlearning sortable unlearning
Language:HTML 4
unlearning-challenge / unlearning-challenge.github.io
challenge competition kaggle-competition machine-learning unlearning
Language:Ruby 3
gthaka / demo-springboot
Unlearning Java, with Spring boot. AmigosCode https://youtu.be/9SGDpanrc8U
java spring-boot unlearning
Language:Java 2