AI Paper Atlas

Research map / Adversarial robustness and security / Backdoor and poisoning

On the Trade-off between Adversarial and Backdoor Robustness

Cheng-Hsin Weng, Yan-Ting Lee, Shan-Hung (Brandon) Wu

NeurIPS 2020 · Adversarial robustness and security › Backdoor and poisoning · approach: Trigger-based backdoor attacks · 21 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
apply adversarial trainingstandard network · MNISTbackdoor attack success rate: 17.2% -> 67.2%Hurt
apply adversarial trainingstandard network · CIFAR-10backdoor attack success rate: 64.1% -> 99.9%Hurt
apply adversarial trainingstandard network · ImageNetbackdoor attack success rate: 3.9% -> 65.4%Hurt
apply adversarial trainingstandard network · CIFAR-10clean accuracy: 90% -> 79.3%Hurt
apply adversarial trainingstandard network · ImageNetadversarial robustness: 0.1% -> 18.4%Improved
add Lipschitz regularization or denoising layers without adversarial trainingstandard network · MNISTadversarial robustness: 0% -> 0%No clear effect
apply certified defense IBPstandard network · MNISTbackdoor attack success rate: 36.3% -> 92.4%Hurt
shrink trigger to 1x1 on adversarially trained networkadversarially trained network · CIFAR-10backdoor success rate: 31.1% -> 69.8%Mixed
use spectral signatures defense against clean-label attack on adversarially trained modelpre-training backdoor defense · CIFAR-10poison detection rate: 24.4% -> 10.6%Hurt
apply neural cleansing to adversarially trained model vs standard modelpost-training backdoor defense · CIFAR-10 complex watermarkbackdoor success rate after defense: 39.3% -> 1.2%Improved

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