[New Model] <Zhang2024CausalDiff>

[ZhangMingKun1]

Paper Information

• Paper Title: CausalDiff: Causality-Inspired Disentanglement via Diffusion Model for Adversarial Defense
• Paper URL: https://arxiv.org/pdf/2410.23091
• Paper authors: Mingkun Zhang, Keping Bi, Wei Chen, Quanrun Chen, Jiafeng Guo, Xueqi Cheng

Leaderboard Claim(s)

Add here the claim for your model(s). Copy and paste the following subsection for the number of models you want to add.

Model 1

• Architecture: Diffusion
• Dataset: CIFAR-10
• Threat Model: Linf
• eps: 8/255
• Clean accuracy: 90.23
• Robust accuracy: 83.01
• Additional data: false
• Evaluation method: AutoAttack
• Checkpoint and code: checkpoint and code

Model 2

• Architecture: Diffusion
• Dataset: CIFAR-10
• Threat Model: L2
• eps: 8/255
• Clean accuracy: 90.23
• Robust accuracy: 86.33
• Additional data: false
• Evaluation method: AutoAttack
• Checkpoint and code: checkpoint and code (same with Model 1)

Model Zoo:

• I want to add my models to the Model Zoo (check if true)
• I use an architecture that is included among
  those here or in timm. If not, I added the link to the architecture implementation so that it can be added.
• I agree to release my model(s) under MIT license (check if true) OR under a custom license, located here: (put the custom license URL here if a custom license is needed. If no URL is specified, we assume that you are fine with MIT)

[fra31]

Hi,

thanks for the submission! If I understand your approach correctly, it involves both optimization loops and randomness. Both these aspects would violate the requirements for models to appear on the leaderboards (see e.g. here).

[ZhangMingKun1]

OK. I got it. Thank you for your response.