-
Notifications
You must be signed in to change notification settings - Fork 215
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
Implement integration of CrowdGuard #903
Conversation
Signed-off-by: Phillip Rieger <[email protected]>
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"# Copyright (C) 2020-2022 TU Darmstadt\n", |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Should this be updated to 2023?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I just uploaded the fix for the warnings. Unfortunately, I'm not sure, if I can trigger the workflows myself. Could you re-run them?
Signed-off-by: Phillip Rieger <[email protected]>
Signed-off-by: Phillip Rieger <[email protected]>
Signed-off-by: Phillip Rieger <[email protected]>
Signed-off-by: Phillip Rieger <[email protected]>
* Implement integration of CrowdGuard Signed-off-by: Phillip Rieger <[email protected]> * Fix formatting Signed-off-by: Phillip Rieger <[email protected]> * fix lint checks Signed-off-by: Phillip Rieger <[email protected]> * outsource pretrained model Signed-off-by: Phillip Rieger <[email protected]> * Add note that execution inside TEEs will be added in the future Signed-off-by: Phillip Rieger <[email protected]> --------- Signed-off-by: Phillip Rieger <[email protected]> Co-authored-by: Phillip Rieger <[email protected]> Signed-off-by: nammbash <[email protected]>
* Implement integration of CrowdGuard Signed-off-by: Phillip Rieger <[email protected]> * Fix formatting Signed-off-by: Phillip Rieger <[email protected]> * fix lint checks Signed-off-by: Phillip Rieger <[email protected]> * outsource pretrained model Signed-off-by: Phillip Rieger <[email protected]> * Add note that execution inside TEEs will be added in the future Signed-off-by: Phillip Rieger <[email protected]> --------- Signed-off-by: Phillip Rieger <[email protected]> Co-authored-by: Phillip Rieger <[email protected]> Signed-off-by: nammbash <[email protected]>
* Implement integration of CrowdGuard Signed-off-by: Phillip Rieger <[email protected]> * Fix formatting Signed-off-by: Phillip Rieger <[email protected]> * fix lint checks Signed-off-by: Phillip Rieger <[email protected]> * outsource pretrained model Signed-off-by: Phillip Rieger <[email protected]> * Add note that execution inside TEEs will be added in the future Signed-off-by: Phillip Rieger <[email protected]> --------- Signed-off-by: Phillip Rieger <[email protected]> Co-authored-by: Phillip Rieger <[email protected]> Signed-off-by: nammbash <[email protected]>
* Implement integration of CrowdGuard Signed-off-by: Phillip Rieger <[email protected]> * Fix formatting Signed-off-by: Phillip Rieger <[email protected]> * fix lint checks Signed-off-by: Phillip Rieger <[email protected]> * outsource pretrained model Signed-off-by: Phillip Rieger <[email protected]> * Add note that execution inside TEEs will be added in the future Signed-off-by: Phillip Rieger <[email protected]> --------- Signed-off-by: Phillip Rieger <[email protected]> Co-authored-by: Phillip Rieger <[email protected]> Signed-off-by: nammbash <[email protected]>
* Implement integration of CrowdGuard Signed-off-by: Phillip Rieger <[email protected]> * Fix formatting Signed-off-by: Phillip Rieger <[email protected]> * fix lint checks Signed-off-by: Phillip Rieger <[email protected]> * outsource pretrained model Signed-off-by: Phillip Rieger <[email protected]> * Add note that execution inside TEEs will be added in the future Signed-off-by: Phillip Rieger <[email protected]> --------- Signed-off-by: Phillip Rieger <[email protected]> Co-authored-by: Phillip Rieger <[email protected]> Signed-off-by: manuelhsantana <[email protected]>
We added a demo implementation of the backdoor defense CrowdGuard (to appear at NDSS 2024) to the tutorial folder.
To demonstrate CrowdGuard's effectiveness, we added a scenario where malicious clients perform a poisoning attack. The poisoning attack is implemented through one code file (cifar10_crowdguard.py) as well as two interactive notebooks. The notebook PoisoningAttackDemo.ipynb is self-contained, while the other notebook (PoisoningAttackDemoReduced.ipynb) imports reused functions and classes from cifar10_crowdguard.py