MinChen00/UnlearningLeaks
Official implementation of "When Machine Unlearning Jeopardizes Privacy" (ACM CCS 2021)
PythonGPL-3.0
Issues
- 1
- 0
All metric (train/test acc/auc) yields 0.5 when training from scratch with Logistic Regression
#9 opened by fengxijia - 0
The neg samples had exactly the same output on the original model and the unlearning model
#8 opened by Aicyanic - 4
- 3
- 1
- 1
- 1
We are expecting this SOTA MIA!
#1 opened by EchizenG - 1
We are expecting this code!
#2 opened by yaolu-zjut