6 results found Sort:

zjunlp
EasyEdit zjunlp
182
1.5k
mit
19
An Easy-to-use Knowledge Editing Framework for LLMs.
gpt tool llama knowlm llama2 mmedit chatgpt mistral baichuan easyedit safeedit efficient unlearning model-editing trustworthy-ai knowledge-editing open-source-project large-language-models artificial-intelligence natural-language-processing
Created 2023-05-09
905 commits to main branch, last one a day ago
tamlhp
awesome-machine-unlearning tamlhp
49
617
mit
14
Awesome Machine Unlearning (A Survey of Machine Unlearning)
gdpr forgetting unlearning data-privacy data-removal data-deletion llm-unlearning deep-unlearning feature-injection continual-learning machine-unlearning few-shot-unlearning model-certification federated-unlearning membership-inference right-to-be-forgotten unlearning-verification recommendation-unlearning
Created 2022-07-07
165 commits to main branch, last one a day ago
OPTML-Group
Unlearn-Saliency OPTML-Group
9
76
mit
0
[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, Denn...
diffusion forgetting unlearning data-privacy data-removal data-deletion diffusion-models generative-model machine-unlearning membership-inference membership-inference-attack
Created 2023-10-12
47 commits to master branch, last one 5 days ago
OPTML-Group
Unlearn-Sparse OPTML-Group
6
53
mit
2
[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
forgetting unlearning data-privacy data-removal data-deletion machine-unlearning membership-inference membership-inference-attack
Created 2023-02-03
105 commits to public branch, last one 2 months ago
OPTML-Group
Diffusion-MU-Attack OPTML-Group
2
30
mit
1
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 effectiv...
robustness unlearning stable-diffusion adversarial-attacks evaluation-framework attack-unlearned-diffusion-model
Created 2023-10-17
53 commits to main branch, last one 5 days ago
chrisliu298
awesome-llm-unlearning chrisliu298
0
28
apache-2.0
1
A resource repository for machine unlearning in large language models
llm awesome alignment unlearning llm-unlearning machine-unlearning large-language-model
Created 2024-03-27
33 commits to main branch, last one a day ago