bolunwang backdoor issues - Githubissues

bolunwang / backdoor

Code implementation of the paper "Neural Cleanse: Identifying and Mitigating Backdoor Attacks in Neural Networks", at IEEE Security and Privacy 2019.

https://sandlab.cs.uchicago.edu/

MIT License

267 stars 63 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

URL does not exist

#18 chengyiqiu1121 opened 8 months ago
0
the code

#17 KDluo opened 1 year ago
1
reg_best does not converge

#16 snutesh opened 1 year ago
0
The download link of data is invaild

#15 Kolt1911 opened 1 year ago
0
Is this detection method a white-box setting?

#14 tonggege001 closed 3 years ago
2
where is implementation on partial backdoor attack?

#13 Kataang closed 2 years ago
1
The reversed mask of the targetted label can't converge on MNIST dataset

#12 Crane-Mocker closed 3 years ago
1
y_true and y_pred position

#11 shihongf closed 3 years ago
2
implementation on other datasets?

#10 ZJZAC closed 3 years ago
1
Adaptation for partial backdoor attack

#9 Xavierxhq closed 4 years ago
2
Watermark pattern might be incorrect

#8 mvillarreal14 closed 4 years ago
1
Reverse-engineered triggers: can you share them?

#7 mvillarreal14 closed 4 years ago
1
Information about VGGFace models is missing: can you add it?

#6 mvillarreal14 closed 4 years ago
4
About data poisoning

#5 tiroshenao closed 4 years ago
1
As for detailed model construction file

#4 Yi2Zhao closed 5 years ago
4
trigger pattern mentioned in the paper

#3 jiashenC closed 5 years ago
2
The Reverse Engineering output is not correct

#2 kaidi-jin closed 5 years ago
4
Detection Ineffective on MNIST model

#1 ChengFu0118 closed 5 years ago
3