Skip to content

Source code for Membership Inference Attacks on Machine Learning Models: Analysis and Mitigation

Notifications You must be signed in to change notification settings

ShamimurRahmanShuvo/Membership-Inference-Attacks-Mitigation

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

12 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Membership-Inference-Attacks-Mitigation

Source code for Membership Inference Attacks on Machine Learning Models: Analysis and Mitigation

It contains protects the membership attack for three different algorithms:

  1. Feed-Forward Neural Network
  2. Convolutional Neural Network
  3. Logistic Regression

Different methodologies like adversarial noise layer, Gaussian noise layer and exponential mechanisms were used to preserve the privacy of the machine learning models from membership inference attack.

If you use any of these code please cite:

Shuvo, Md Shamimur Rahman, and Dima Alhadidi. "Membership Inference Attacks: Analysis and Mitigation." 2020 IEEE 19th International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom). IEEE, 2020.

About

Source code for Membership Inference Attacks on Machine Learning Models: Analysis and Mitigation

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages