Search Results for author:
Found 6 papers, 2 papers with code
Continual Learning in the Presence of Repetition
Continual learning (CL) provides a framework for training models in ever-evolving environments.
Improving Adversarial Robust Fairness via Anti-Bias Soft Label Distillation
In this paper, we give an in-depth analysis of the potential factors and argue that the smoothness degree of samples' soft labels for different classes (i. e., hard class or easy class) will affect the robust fairness of DNN models from both empirical observation and theoretical analysis.
Mitigating the Accuracy-Robustness Trade-off via Multi-Teacher Adversarial Distillation
Adversarial training is a practical approach for improving the robustness of deep neural networks against adversarial attacks.
Boosting Adversarial Transferability with Learnable Patch-wise Masks
The proposed approach is a preprocessing method and can be integrated with existing methods to further boost the transferability.
Revisiting the Trade-off between Accuracy and Robustness via Weight Distribution of Filters
Secondly, based on this observation, we propose a sample-wise dynamic network architecture named Adversarial Weight-Varied Network (AW-Net), which focuses on dealing with clean and adversarial examples with a ``divide and rule" weight strategy.
Preventing Unauthorized AI Over-Analysis by Medical Image Adversarial Watermarking
The advancement of deep learning has facilitated the integration of Artificial Intelligence (AI) into clinical practices, particularly in computer-aided diagnosis.
