-
Notifications
You must be signed in to change notification settings - Fork 76
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
关于IBD—IPS在Ciafr-10数据下采用Badnet攻击的Resnet-18模型AUROC低的疑问 #89
Comments
您好!我通过调整目标标签和触发器图案,观察到攻击成功率(ASR)发生了变化,并且这些变化与训练日志记录的结果不一致。这证实了我最初的触发器、目标标签以及模型配置是正确的。 |
github上传似乎失败,无法下载。我上传到了百度云盘。链接:https://pan.baidu.com/s/1y3zuJbLepWtM8sp2ixQLfQ?pwd=vhdx |
请问你跑了SCALE_UP吗,我这边跑出来的AUC只有0.5几,请问你知道是什么原因吗 |
|
是Bandet攻击吗,SCALE_UP在白色和黑色以及黑白触发器的效果不好,IBD_IPS论文中有讲 |
你好 我们刚刚上传了target label分别为0和1的两个在CIFAR-10上训练好的BadNets后门模型(效果展示图已经贴在上面的回答中)。触发器为默认设置: |
您好,我利用BackdoorBox提供的代码训练了一个Resnet-18网络
我们利用IBD—IPS评估时的ASR和BA和训练中的数据一致
但检测的效果不好,ROC仅0.7
请问是哪儿出了问题,是选取的BN放大层出了问题吗
The text was updated successfully, but these errors were encountered: