search

Trusted-AI / adversarial-robustness-toolbox

Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference - Red and Blue Teams
https://adversarial-robustness-toolbox.readthedocs.io/en/latest/
MIT License
4.75k stars 1.15k forks source link

Incorrect import statements in notebooks/attack_membership_inference.ipynb #897

Closed evansakmar closed 3 years ago

evansakmar commented 3 years ago

Describe the bug Incorrect import statements in _notebooks/attack_membershipinference.ipynb

To Reproduce Steps to reproduce the behavior: Start the notebook _notebooks/attack_membershipinference.ipynb

Both "Rule-based attack" and "Train attack model" fail to run due to import errors.

---------------------------------------------------------------------------
ImportError                               Traceback (most recent call last)
<ipython-input-3-e4caf591daac> in <module>()
      1 import numpy as np
----> 2 from art.attacks.inference import MembershipInferenceBlackBoxRuleBased
      3 
      4 attack = MembershipInferenceBlackBoxRuleBased(art_classifier)
      5 

ImportError: cannot import name 'MembershipInferenceBlackBoxRuleBased'

Expected behavior Should import the classes and run the code.

System information (please complete the following information):

evansakmar commented 3 years ago

I have an incoming pull request for this.

beat-buesser commented 3 years ago

Hi @evansakmar Thank you very much, that's really great!