7 papers
Adaptive Causal Alignment for High-Confidence Adversarial Training
Zhiming Luo, Kejia Zhang, Yingxin Lai +3
Inverse adversarial training leverages high-confidence predictions to stabilize robust learning, yet we uncover a critical paradox: high confidence often stems from overfitting to…
Towards Adversarial Robustness via Debiased High-Confidence Logit Alignment
Kejia Zhang, Juanjuan Weng, Shaozi Li +1
Despite the remarkable progress of deep neural networks (DNNs) in various visual tasks, their vulnerability to adversarial examples raises significant security concerns. Recent adv…
Mitigating Low-Frequency Bias: Feature Recalibration and Frequency Attention Regularization for Adversarial Robustness
Kejia Zhang, Juanjuan Weng, Yuanzheng Cai +2
Ensuring the robustness of deep neural networks against adversarial attacks remains a fundamental challenge in computer vision. While adversarial training (AT) has emerged as a pro…
Long-Tailed Out-of-Distribution Detection: Prioritizing Attention to Tail
Yina He, Lei Peng, Yongcun Zhang +3
Current out-of-distribution (OOD) detection methods typically assume balanced in-distribution (ID) data, while most real-world data follow a long-tailed distribution. Previous appr…
Harmonizing Feature Maps: A Graph Convolutional Approach for Enhancing Adversarial Robustness
Kejia Zhang, Juanjuan Weng, Junwei Wu +3
The vulnerability of Deep Neural Networks to adversarial perturbations presents significant security concerns, as the imperceptible perturbations can contaminate the feature space…
Improving Transferable Targeted Adversarial Attack via Normalized Logit Calibration and Truncated Feature Mixing
Juanjuan Weng, Zhiming Luo, Shaozi Li
This paper aims to enhance the transferability of adversarial samples in targeted attacks, where attack success rates remain comparatively low. To achieve this objective, we propos…