Zhengzhou University of Light Industry

2 related articles

Subscribe to updates

researchsquare.com Nov 11, 2026
Backdoor detection stops reading only the last layer: CLEAR fuses cross-layer extreme responses for 99.54% average TPR on Tiny-ImageNet
CLEAR moves backdoor sample detection from single-layer activations to cross-layer extreme responses: batch normalization statistics align hidden-layer features to a common scale, each channel's spatial minimum becomes the anomaly representation, and particle swarm optimization searches layer weights. On CIFAR-10 and Tiny-ImageNet, CLEAR reaches average true positive rates of 97.54% and 99.54% with average false positive rates of 0.16% and 0.03%, above AC, SCALE-UP, AIBD and CCD; models retrained on its purified data stay close to benign accuracy.
CLEAR moves backdoor sample detection from single-layer activations to cross-layer extreme responses: batch normalization statistics align hidden-layer features to a common scale, each channel's spatial minimum becomes the anomaly representation, and particle swarm optimization searches layer weights. On CIFAR-10 and Tiny-ImageNet, CLEAR reaches average true positive rates of 97.54% and 99.54% with average false positive rates of 0.16% and 0.03%, above AC, SCALE-UP, AIBD and CCD; models retrained on its purified data stay close to benign accuracy.
Zhengzhou University of Economics and Business China Railway Group (China)Zhengzhou University Zhengzhou University of Light Industry
Hui Li（First author）Wanwei Huang（Corresponding author）
CLEAR Backdoor Detection Particle Swarm Optimization Clustering
researchsquare.com Oct 23, 2026
Alzheimer's diagnosis moves to two brain graphs: AD versus CN accuracy rises from 82.06% to 89.90%
Structural MRI brain graphs no longer rely on a single predefined connection rule. MVMGNN treats brain regions as nodes carrying radiomics features, builds a spatial-neighbor graph and a feature-similarity graph, filters redundant features and weak connections inside each view with a joint node-edge mask, and fuses the two views through patient-level gated fusion. On the ADNI cohort, AD versus CN accuracy rises from 82.06% for the best comparison method, RSEA-MVGNN, to 89.90%, and F1 from 75.02% to 86.24%; gains on the harder AD-MCI and CN-MCI tasks are smaller.
Structural MRI brain graphs no longer rely on a single predefined connection rule. MVMGNN treats brain regions as nodes carrying radiomics features, builds a spatial-neighbor graph and a feature-similarity graph, filters redundant features and weak connections inside each view with a joint node-edge mask, and fuses the two views through patient-level gated fusion. On the ADNI cohort, AD versus CN accuracy rises from 82.06% for the best comparison method, RSEA-MVGNN, to 89.90%, and F1 from 75.02% to 86.24%; gains on the harder AD-MCI and CN-MCI tasks are smaller.
Michigan Technological University Kennesaw State University Zhengzhou University of Light Industry
Ni Yao（First author）
Radiomics Graph Neural Network Multimodal Fusion

You’re all caught up

Backdoor detection stops reading only the last layer: CLEAR fuses cross-layer extreme responses for 99.54% average TPR on Tiny-ImageNet

Alzheimer's diagnosis moves to two brain graphs: AD versus CN accuracy rises from 82.06% to 89.90%