membership-inference topic

Privacy Testing for Deep Learning

trailofbits

Security and Privacy Risk Simulator for Machine Learning (arXiv:2312.17667)

Koukyosyumei

Awesome Machine Unlearning (A Survey of Machine Unlearning)

tamlhp

reveal the vulnerabilities of SplitNN

Koukyosyumei

[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...

OPTML-Group

[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

OPTML-Group

Python package for measuring memorization in LLMs.

iamgroot42