arXiv Machine Learning
Theoretical Lower Bounds on the Robustness of Deep ReLU Networks
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Jun 16
Upper Bounds on the Generalization Error of Deep Learning Models via Local Robustness and Stability
arXiv:2606. 16883v1 Announce Type: cross Abstract: Generalization is a critical property of data-driven models, particularly deep learning models deployed in safety-critical applications.
arXiv Machine Learning
Jun 26
The Role of Input Dimensionality in the Emergence and Targeted Control of Adversarial Examples
arXiv:2606. 26207v1 Announce Type: cross Abstract: Several theoretical works have tried to explain the adversarial vulnerability of deep neural networks through properties of high-dimensional geometry.
arXiv Machine Learning
Jul 1
Robustness of neural networks to random noise perturbations of their inputs
arXiv:2606. 31581v1 Announce Type: new Abstract: We investigate the problem of the robustness of a trained neural network to the perturbation of its input values.
arXiv AI
Jun 24
Are Safety Guarantees in Neural Networks Safe? How to Compute Trustworthy Robustness Certifications
arXiv:2606. 23858v1 Announce Type: cross Abstract: A primary challenge in AI safety is the existence of adversarial examples -- slightly distorted inputs that cause a neural network (NN) to misclassify.
arXiv Machine Learning
Jun 9
Characterizing the Discrete Geometry of ReLU Networks
arXiv:2606. 07728v1 Announce Type: new Abstract: It is well established that ReLU networks define continuous piecewise-linear functions, and that their linear regions are polyhedra in the input space.
arXiv Machine Learning
Jun 4
Measuring Model Robustness via Fisher Information: Spectral Bounds, Theoretical Guarantees, and Practical Algorithms
arXiv:2606. 04767v1 Announce Type: new Abstract: The robustness of deep neural networks is crucial for safety-critical deployments, yet existing evaluation methods are often attack-dependent and lack interpretability.