AI Paper Atlas

Research map / Adversarial robustness and security / Backdoor and poisoning

Detecting Backdoors During the Inference Stage Based on Corruption Robustness Consistency

Xiaogeng Liu, Minghui Li, Haoyu Wang, Shengshan Hu, Dengpan Ye, Hai Jin, Libing Wu, Chaowei Xiao

CVPR 2023 · Adversarial robustness and security › Backdoor and poisoning · approach: Training-time backdoor defense · 34 citations (OpenAlex)

Read the paper

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 corruption-severity transition dispersion with hard-label outputs for test-time trigger detectionTeCo · CIFAR10, PreActResNet18AUROC: 0.584 -> 0.918 (STRIP); 0.888 -> 0.918 (FreqDetector)Improved
Use corruption-severity transition dispersion with hard-label outputs for test-time trigger detectionTeCo · GTSRB, PreActResNet18AUROC: 0.690 -> 0.940 (STRIP); 0.784 -> 0.940 (FreqDetector)Improved
Increase maximum corruption severity N (ablation)TeCo · Multiple datasets and CNN/ViT backbonesAUROCMixed
Vary the predefined target label (ablation)TeCo · GTSRB: Blended, SSBA, and Wanet attacksAUROC: Blended AUROC ≥0.874, STD about 0.021; SSBA AUROC ≥0.908, STD ≈0.010; Wanet AUROC ≥0.919, STD ≈0.017No clear effect
Add an adaptive loss that aligns corruption robustness of clean and trigger inputs to backdoor training (ablation)Backdoor models evaluated by TeCo · CIFAR10, PreActResNet18, BadNetsAUROC: 0.9112 -> 0.5763 (10^-3); 0.9112 -> 0.6571 (10^-4); 0.9112 -> 0.6745 (10^-5)Hurt
Add an adaptive loss that aligns corruption robustness of clean and trigger inputs to backdoor training (ablation)Backdoor models evaluated by TeCo · CIFAR10, PreActResNet18, SSBAAUROC: 0.8683 -> 0.7125 (10^-3); 0.8683 -> 0.6477 (10^-4); 0.8683 -> 0.5909 (10^-5)Hurt
Add an adaptive loss that aligns corruption robustness of clean and trigger inputs to backdoor training (ablation)Backdoor models evaluated by TeCo · CIFAR10, PreActResNet18, LFAUROC: 0.9390 -> 0.8592 (10^-3); 0.9390 -> 0.9219 (10^-4); 0.9390 -> 0.8667 (10^-5)Mixed
Use one empirical threshold γ=1 across attacks (ablation)TeCo · Multiple datasets and CNN/ViT backbonesaccuracy: CNN AVG 0.7923; ViT AVG 0.7868Mixed

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