A unified, easily extensible repository for LLM unlearning benchmarks (TOFU, MUSE) - enabling new datasets, evaluations, methods, and tasks.

[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

The official implementation of ECCV'24 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.

RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models. NeurIPS 2024

[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

Continual Forgetting for Pre-trained Vision Models (CVPR 2024)

[ACL 2024] Code and data for "Machine Unlearning of Pre-trained Large Language Models"

[EMNLP 2024] To Forget or Not? Towards Practical Knowledge Unlearning for Large Language Models

Code for implementation of Unlearning Scanner Bias for MRI Harmonisation

[NeurIPS 2024] Large Language Model Unlearning via Embedding-Corrupted Prompts

[ECCV24] "Challenging Forgets: Unveiling the Worst-Case Forget Sets in Machine Unlearning" by Chongyu Fan*, Jiancheng Liu*, Alfred Hero, Sijia Liu

Pytorch implementation of backdoor unlearning.

Implementation for MICCAI DART paper: 'Detecting Melanoma Fairly: Skin Tone Detection and Debiasing for Skin Lesion Classification'

Implementation of paper 'Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Difference' [NeurIPS'24]

Knowledge Unlearning for Large Language Models

Official Code of Learning to Unlearn: Instance-Wise Unlearning for Pre-trained Classifiers (AAAI 2024)

Experiments for our CLEAR benchmark of unlearning methods in a multimodal setup

Implementation for ICML 2022 paper: 'Skin Deep Unlearning: Artefact and Instrument Debiasing in the Context of Melanoma Classification'

Demystifying Verbatim Memorization in Large Language Models

Machine Unlearning Framework