IBM/Autozoom-Attack
Codes for reproducing query-efficient black-box attacks in “AutoZOOM: Autoencoder-based Zeroth Order Optimization Method for Attacking Black-box Neural Networks” , published at AAAI 2019
PythonApache-2.0
Issues
- 6
- 0
- 1
- 0
bug report
#15 opened by lin2020 - 1
- 1
- 16
What is the input image pixel's range?
#10 opened by machanic - 1
Bug report, the attacked classification model does not load any pre-trained weights!
#13 opened by machanic - 1
Question about tf.log usage
#12 opened by machanic - 3
- 1
- 1
Question about the modifiers
#4 opened by dongyp13 - 9
- 1
- 1
- 0
- 0
Question about attacking to the ResNet
#5 opened by yxwang-10 - 2
L2dist can‘t convergence
#2 opened by wzp123456 - 1
Question on the code
#1 opened by dssrgu