AI Paper Atlas

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

Learning to Confuse: Generating Training Time Adversarial Data with Auto-Encoder

Ji Feng, Qi-Zhi Cai, Zhi-Hua Zhou

NeurIPS 2019 · Adversarial robustness and security › Certified and empirical robustness · approach: Regularized defenses against attacks · 14 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
Train on bounded adversarial data generated to reduce clean-test performanceCNN · MNIST testaccuracy: $99.32\pm0.05$ -> $0.25\pm0.04$Hurt
Train on bounded adversarial data generated to reduce clean-test performanceCNN · ImageNet (bulbul vs. jellyfish) testaccuracy: $88.5\pm2.32$ -> $54.2\pm11.19$Hurt
Train on bounded adversarial data generated to reduce clean-test performanceCNN · CIFAR-10 testaccuracy: $77.28\pm 0.17$ -> $28.77\pm2.80$Hurt
Use a label-specific objective to shift predictions to predefined target labelsDeep Confuse · MNIST testtargeted attack success rate: 0.00 -> $79.7\pm0.38$Improved
Use a label-specific objective to shift predictions to predefined target labelsDeep Confuse · MNIST testaccuracy: $0.25\pm0.04$ -> $1.48\pm0.21$Hurt
Evaluate classifiers trained on generated noise aloneDeep Confuse-trained CNN · MNIST testaccuracy using noise-only inputs: 95.15Improved
Evaluate classifiers trained on generated noise aloneDeep Confuse-trained CNN · ImageNet testaccuracy using noise-only inputs: 93.00Improved
Evaluate classifiers trained on generated noise aloneDeep Confuse-trained CNN · CIFAR-10 testaccuracy using noise-only inputs: 72.98Improved
Transfer generated adversarial training data to classifiers with different architectures or model typesDeep Confuse · MNIST, CIFAR-10, and ImageNettest performanceHurt

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