Neural Network Robustness

Towards Adversarial Robustness via Debiased High-Confidence Logit Alignment
Towards Adversarial Robustness via Debiased High-Confidence Logit Alignment

An interesting attempt to explore inverse adversarial attacks to enhance adversarial robustness.

Jul 25, 2024

Mitigating Low-Frequency Bias: Feature Recalibration and Frequency Attention Regularization for Adversarial Robustness
Mitigating Low-Frequency Bias: Feature Recalibration and Frequency Attention Regularization for Adversarial Robustness

A frequency perspective to construct robust model.

Jul 15, 2024

Harmonizing Feature Maps: A Graph Convolutional Approach for Enhancing Adversarial Robustness
Harmonizing Feature Maps: A Graph Convolutional Approach for Enhancing Adversarial Robustness

This is an interesting attempt to apply graph neural networks to visual tasks.

May 1, 2024