AI Paper Atlas

Research map / Adversarial robustness and security / Backdoor and poisoning

Data-Free Backdoor Removal Based on Channel Lipschitzness

Runkai Zheng, Rongjun Tang, Jianze Li, Li Liu

ECCV 2022 · Adversarial robustness and security › Backdoor and poisoning · approach: Training-time backdoor defense · 97 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 CLP (data-free channel pruning) to backdoored modelResNet-18 · CIFAR-10 (average over 7 attacks)ASR (%): 98.72 -> 2.81Improved
apply CLP to backdoored modelResNet-18 · Tiny ImageNet (average over 7 attacks)ASR (%): 97.47 -> 1.89Improved
use CLP instead of ANP with 500 benign samplesANP · CIFAR-10 (average over 7 attacks)ASR (%): 18.23 -> 2.81Improved
use CLP instead of ANP with 1,000 benign samplesANP · Tiny ImageNet (average over 7 attacks)ASR (%): 17.62 -> 1.89Improved
use CLP instead of NADNAD · CIFAR-10 (average over 7 attacks)ACC (%): 92.78 -> 93.36Improved
use CLP instead of NADNAD · Tiny ImageNet (average over 7 attacks)ASR (%): 62.13 -> 1.89Improved
use CLP instead of fine-tuning on CIFAR-10 for CLA attackFT · CIFAR-10 (CLA)ASR (%): 0.39 -> 2.84Hurt
use CLP instead of NAD on BlendedNAD · CIFAR-10 (Blended)ASR (%): 1.61 -> 1.90Hurt
lower poisoning rate from 10% to 1% for CLA, then apply CLP (ablation)CLP · CIFAR-10 (CLA)ASR (%): 2.84 -> 10.04Hurt
vary poisoning rate (1%, 5%, 10%) before applying CLP (ablation)CLP · CIFAR-10 (BadNets, Trojan, Blended, A2A)ASR (%): 0.76No clear effect
lower pruning threshold u toward 0 (ablation)CLP · CIFAR-10 (ResNet-18)ASR and ACCMixed
use u=3 or 4 across ResNet/VGG/SENet architectures instead of per-architecture u (ablation)CLP · CIFAR-10 (BadNets, various CNNs)ASR and ACCMixed

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