Search Results for author:
Found 4 papers, 1 papers with code
1-Lipschitz Layers Compared: Memory, Speed, and Certifiable Robustness
The robustness of neural networks against input perturbations with bounded magnitude represents a serious concern in the deployment of deep learning models in safety-critical systems.
Robust-by-Design Classification via Unitary-Gradient Neural Networks
This work proposes a novel family of classifiers, namely Signed Distance Classifiers (SDCs), that, from a theoretical perspective, directly output the exact distance of x from the classification boundary, rather than a probability score (e. g., SoftMax).
Defending From Physically-Realizable Adversarial Attacks Through Internal Over-Activation Analysis
This work presents Z-Mask, a robust and effective strategy to improve the adversarial robustness of convolutional networks against physically-realizable adversarial attacks.
On the Minimal Adversarial Perturbation for Deep Neural Networks with Provable Estimation Error
In this regard, the Euclidean distance of the input from the classification boundary denotes a well-proved robustness assessment as the minimal affordable adversarial perturbation.
