AI Paper Atlas

Research map / Adversarial robustness and security / Black-box and transfer attacks

Improving Adversarial Robustness via Probabilistically Compact Loss with Logit Constraints

Xin Li, Xiangrui Li, Deng Pan, Dongxiao Zhu

AAAI 2021 · Adversarial robustness and security › Black-box and transfer attacks · approach: Robustness benchmarks and defenses · 12 citations (OpenAlex)

Read the paper

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
Replace CE with PC loss and logit constraintsVGG-13 · CIFAR-100 PGD, 0.005accuracy: 24.4 -> 56.7Improved
Replace CE with PC loss and logit constraintsVGG-13 · Tiny ImageNet PGD, 0.005accuracy: 11.3 -> 24.8Improved
Replace CE with PC loss and logit constraintsLeNet-5 · MNIST PGD, 0.1accuracy: 49.0 -> 72.3Improved
Replace CE with PC loss and logit constraintsVGG-13 · CIFAR-10 PGD, 0.04accuracy: 0.0 -> 27.6Improved
Replace CE with PC loss and logit constraintsLeNet-5 · MNIST cleanaccuracy: 99.2 -> 99.2No clear effect
Replace CE with PC loss and logit constraintsVGG-13 · CIFAR-10 cleanaccuracy: 91.6 -> 91.2No clear effect
Replace GCE with PC loss and logit constraintsResNet-56 · CIFAR-10 FGSM, 0.04accuracy: 41.2 -> 58.4Improved
Replace GCE with PC loss and logit constraintsLeNet-5 · MNIST FGSM, 0.1accuracy: 87.7 -> 80.5Hurt

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