issues
search
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
https://arxiv.org/abs/1805.11770
Apache License 2.0
56
stars
22
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
BUG report : TypeError: unhashable type 'slice' , orz plz
#19
bambooboy
opened
3 years ago
6
that Total testing data:250, correct classified data:0
#18
Mah-SP
opened
3 years ago
0
Could you please provide the code of training the decoder.h5 and encoder.h5?
#17
chl2
opened
3 years ago
1
What shoult I do if I want to use this algorithm in orther models and dataset?
#16
chl2
opened
4 years ago
1
bug report
#15
lin2020
closed
4 years ago
0
Can I ask you a question about a terminology of adversarial attack?
#14
machanic
opened
4 years ago
1
Bug report, the attacked classification model does not load any pre-trained weights!
#13
machanic
opened
4 years ago
1
Question about tf.log usage
#12
machanic
opened
4 years ago
1
How to count the query number when successful attacked?
#11
machanic
opened
4 years ago
3
What is the input image pixel's range?
#10
machanic
opened
4 years ago
16
Bug report, the compress_mode of ImageNet should be 3
#9
machanic
closed
4 years ago
1
Bug report, self.real_modifier must be cleared before generate next image.
#8
machanic
closed
4 years ago
1
How to convert the auto-encoder h5 file to pytorch format?
#7
machanic
closed
4 years ago
1
Question about USE_TANH in blackbox_attack.py line 222.
#6
Sumching
closed
4 years ago
0
Question about attacking to the ResNet
#5
yxwang-10
closed
4 years ago
0
Question about the modifiers
#4
dongyp13
closed
4 years ago
1
How to get performance of "initial success" attack as reported in the paper?
#3
ZiangYan
closed
4 years ago
9
L2dist can‘t convergence
#2
wzp123456
closed
5 years ago
2
Question on the code
#1
dssrgu
closed
5 years ago
1