AI Paper Atlas

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

Towards Robust Detection of Adversarial Examples

Tianyu Pang, Chao Du, Yinpeng Dong, Jun Zhu

NeurIPS 2018 · Adversarial robustness and security › Certified and empirical robustness · approach: Adversarial training recipes · 13 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 RCE training instead of CE with K-density detectionResnet-32 · MNIST; FGSMAUC score (10^-2): 98.8 -> 99.4Improved
Use RCE training instead of CE with K-density detectionResnet-32 · CIFAR-10; FGSMAUC score (10^-2): 99.7 -> 98.0Hurt
Use RCE training instead of CE with K-density detectionResnet-32 · MNIST; BIMAUC score (10^-2): 90.0 -> 91.8Improved
Use RCE training instead of CE with K-density detectionResnet-32 · CIFAR-10; BIMAUC score (10^-2): 100.0 -> 100.0No clear effect
Use RCE training instead of CE with K-density detectionResnet-32 · MNIST; ILCMAUC score (10^-2): 96.2 -> 98.6Improved
Use RCE training instead of CE with K-density detectionResnet-32 · CIFAR-10; ILCMAUC score (10^-2): 84.2 -> 93.9Improved
Use RCE training instead of CE with K-density detectionResnet-32 · MNIST; JSMAAUC score (10^-2): 97.7 -> 99.0Improved
Use RCE training instead of CE with K-density detectionResnet-32 · CIFAR-10; JSMAAUC score (10^-2): 85.8 -> 95.4Improved
Use RCE training instead of CE with K-density detectionResnet-32 · MNIST; C&WAUC score (10^-2): 99.4 -> 99.8Improved
Use RCE training instead of CE with K-density detectionResnet-32 · CIFAR-10; C&WAUC score (10^-2): 95.3 -> 98.2Improved
Use RCE training instead of CE with K-density detectionResnet-32 · MNIST; C&W-hcAUC score (10^-2): 91.1 -> 99.6Improved
Use RCE training instead of CE with K-density detectionResnet-32 · CIFAR-10; C&W-hcAUC score (10^-2): 75.4 -> 91.8Improved

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