csdongxian/anp_backdoor

Codes for NeurIPS 2021 paper "Adversarial Neuron Pruning Purifies Backdoored Deep Models"

Hi there, I am Dongxian WU (吴栋贤 in Chinese) 👋

I am an enthusiast for building a trustworthy AI system. Currently, I am a Postdoctoral Researcher at the University of Tokyo, hosted by Prof. Masashi Sugiyama.

🔭 My research mainly focus on:

• adversarial attacks and defenses
• data security, especially backdoor attacks and defenses
• weakly supervised learning, especially noisy labels

📫 Reach me by:

• [email protected]
• [email protected]

anp_backdoor's Issues

Could you provide "clb-data"?

Hi, thank you for release the source code. But I didn't find the train and test data of CLB attack. Could you upload the "clb-data"?
Thank you very much!

Some question about the noise.

Hello, thanks for your sharing of the code!
But I have some questions about the code. It seems that the noises are only applied to the BN layers instead of the conv layers in the code. According to the description in the paper, the perturbations to the weight and bias of a neuron may cancel each other out due to the BN layers. So if the network contains the BN layers, the ANP algorithm does only need to perturb the neurons in the BN layers. Otherwise, the ANP algorithm will perturb the neurons in the conv layers. Is that right? Could you please supplement the experimental code for the network that does not contain BN layers?

code issue

Thank you for your generosity, can you provide the source codes of MCR and IAB used in your paper, please?