The standard weighted-average method for adversarial training (AT) in deep learning is suboptimal due to inherent conflict between standard and adversarial gradients, limiting both standard and adversarial accuracy. This paper proposes Conflict-Aware Adversarial Training (CA-AT), a novel approach that mitigates this conflict, enhancing the trade-off between accuracy and robustness.
Overconfidence in predicting adversarial examples during training hinders robust generalization in machine learning models; generating less certain adversarial examples improves robustness and mitigates robust overfitting.
Adversarial training is a powerful technique for enhancing the robustness of deep learning models against adversarial attacks by incorporating adversarial examples into the training process.
2層の多項式活性化ネットワークとReLU活性化ネットワークに対する、効率的で保証された敵対的トレーニングのための新しい凸最適化手法が提案されています。
This research introduces a novel approach to adversarial training for two-layer neural networks with polynomial and ReLU activations, leveraging convex optimization to achieve globally optimal solutions and enhance robustness against adversarial attacks.
This paper challenges the traditional adversarial training paradigm and proposes a novel method, DUCAT, which leverages dummy classes to decouple the learning of benign and adversarial examples, thereby achieving simultaneous improvements in accuracy and robustness.
Standard training of deep neural networks often prioritizes easily perturbed features, making them vulnerable to adversarial examples; however, adversarial training can provably enhance robustness by promoting the learning of robust features.
Die Nutzung historischer Zustände des Zielmodells verbessert die Robustheit und Stabilität von Deep Learning-Modellen.
Data augmentation improves robustness in adversarial training under long-tailed distributions.