Pages that link to "Item:Q2028930"
From MaRDI portal
The following pages link to Adversarial defense via the data-dependent activation, total variation minimization, and adversarial training (Q2028930):
Displaying 17 items.
- Understanding adversarial robustness via critical attacking route (Q2056311) (← links)
- How does momentum benefit deep neural networks architecture design? A few case studies (Q2079522) (← links)
- A robust generative classifier against transfer attacks based on variational auto-encoders (Q2123505) (← links)
- Black-box adversarial attacks by manipulating image attributes (Q2123528) (← links)
- An empirical study of derivative-free-optimization algorithms for targeted black-box attacks in deep neural networks (Q2168625) (← links)
- Theoretical investigation of generalization bounds for adversarial learning of deep neural networks (Q2241474) (← links)
- Graph interpolating activation improves both natural and robust accuracies in data-efficient deep learning (Q5014842) (← links)
- EnResNet: ResNets Ensemble via the Feynman--Kac Formalism for Adversarial Defense and Beyond (Q5037566) (← links)
- Generalization Error Analysis of Neural Networks with Gradient Based Regularization (Q5045671) (← links)
- Unifying Adversarial Training Algorithms with Data Gradient Regularization (Q5380676) (← links)
- Implicit adversarial data augmentation and robustness with noise-based learning (Q6054939) (← links)
- Wavelet regularization benefits adversarial training (Q6074954) (← links)
- Robustifying models against adversarial attacks by Langevin dynamics (Q6078685) (← links)
- A fast saddle-point dynamical system approach to robust deep learning (Q6078719) (← links)
- Lagrangian objective function leads to improved unforeseen attack generalization (Q6134360) (← links)
- A3T: accuracy aware adversarial training (Q6176230) (← links)
- Adversarial Defense via Data Dependent Activation Function and Total Variation Minimization (Q6307121) (← links)
