AI Paper Atlas

Research map / Adversarial robustness and security / Certified and empirical robustness

CUDA: Convolution-Based Unlearnable Datasets

Vinu Sankar Sadasivan, Mahdi Soltanolkotabi, Soheil Feizi

CVPR 2023 · Adversarial robustness and security › Certified and empirical robustness · approach: Augmentation and diffusion purification · 20 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use class-wise convolution filters instead of a universal shared filter (ablation)CIFAR-10 training data · CIFAR-10, ERMclean test accuracy (%): 90.47 -> 18.48Improved
Use CUDA rather than REMResNet-18 with CIFAR-10 · CIFAR-10, L∞ AT (ρa=4/255)clean test accuracy (%): 48.16 -> 44.40Improved
Use CUDA rather than REMResNet-18 with ImageNet-100 · ImageNet-100, L∞ AT (ρa=4/255)clean test accuracy (%): 41.66 -> 38.68Improved
Use CUDA rather than REMResNet-18 with CIFAR-100 · CIFAR-100, L∞ AT (ρa=4/255)clean test accuracy (%): 27.10 -> 34.34Hurt
Increase the L∞ adversarial-training budget from 4/255 to 8/255 (ablation)CIFAR-10 CUDA · CIFAR-10, L∞ ATclean test accuracy (%): 44.40 -> 32.85Improved
Increase the L∞ adversarial-training budget from 4/255 to 16/255 (ablation)CIFAR-10 CUDA · CIFAR-10, L∞ ATclean test accuracy (%): 44.40 -> 19.32Improved
Use L2 AT with budget 0.75 instead of L∞ AT with budget 4/255 (ablation)CIFAR-10 CUDA · CIFAR-10clean test accuracy (%): 44.40 -> 51.14Hurt
Add random blurring augmentation with p′b=0.1 (ablation)CIFAR-10 CUDA training · CIFAR-10clean test accuracy (%): 9.2%Improved
Add random blurring augmentation with p′b=0.3 (ablation)CIFAR-10 CUDA training · CIFAR-10clean test accuracy (%): 13.37%Improved
Add mixup augmentation (ablation)CIFAR-10 CUDA training · CIFAR-10clean test accuracy (%): 25.53%Hurt
Add cutout augmentation (ablation)CIFAR-10 CUDA training · CIFAR-10clean test accuracy (%): 25.80%Hurt
Add cutmix augmentation (ablation)CIFAR-10 CUDA training · CIFAR-10clean test accuracy (%): 26.93%Hurt

Later papers that compared with this method

2 later accepted papers report CUDA as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy