AI Paper Atlas

Research map / Adversarial robustness and security / Backdoor and poisoning

Neural Polarizer: A Lightweight and Effective Backdoor Defense via Purifying Poisoned Features

Mingli Zhu, Shaokui Wei, Hongyuan Zha, Baoyuan Wu

NeurIPS 2023 · Adversarial robustness and security › Backdoor and poisoning · approach: Training-time backdoor defense · 7 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 the learned neural polarizer with the full NPD objective instead of leaving the backdoored model undefendedPreAct-ResNet18 · CIFAR-10, BadNets-A2OASR (%): 93.79 -> 1.26Improved
Use the learned neural polarizer with the full NPD objective instead of leaving the backdoored model undefendedPreAct-ResNet18 · CIFAR-10, BlendedASR (%): 97.71 -> 0.41Improved
Use the learned neural polarizer with the full NPD objective instead of leaving the backdoored model undefendedPreAct-ResNet18 · Tiny ImageNet, 8 attacks (Avg)ASR (%): 89.64 -> 2.17Improved
Use known target labels and targeted universal perturbations (NPD-TU) instead of estimated targets and per-sample perturbations (NPD)NPD · CIFAR-10, 8 attacks (Avg)ASR (%): 1.62 -> 1.02Improved
Use known target labels and per-sample targeted perturbations (NPD-TP) instead of estimated targets and per-sample perturbations (NPD)NPD · CIFAR-10, 8 attacks (Avg)DER (%): 95.56 -> 96.41Improved
Use known target labels and targeted perturbations instead of estimated targetsNPD · Tiny ImageNet, 8 attacks (Avg)DER (%): 90.84 -> 91.46Improved
Replace targeted perturbations with untargeted universal perturbations (ablation)NPD · CIFAR-10, LFASR (%): 0.21 -> 75.42Hurt
Replace targeted perturbations with untargeted PGD perturbations (ablation)NPD · CIFAR-10, LFASR (%): 0.21 -> 17.24Hurt
Add the first boosted-cross-entropy term, which encourages the true label on perturbed samples (ablation)NPD · CIFAR-10, BlendedASR (%): 99.63 -> 2.01Improved
Add the second boosted-cross-entropy term, which suppresses the strongest non-true class (ablation)NPD · CIFAR-10, LFASR (%): 95.90 -> 1.06Improved
Add the attack-success-rate loss term (ablation)NPD · CIFAR-10, LFASR (%): 95.90 -> 0.80Improved
Add all three trigger-purification loss terms (ablation)NPD · CIFAR-10, BadNets-A2OASR (%): 1.18 -> 1.26Mixed

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