3 papers
On Adversarial Vulnerability of Vision-Language Models through the Lens of Intermediate Spectral Subspaces
Chethan Krishnamurthy Ramanaik, Tobias Callies, Michael Hecht +1
Adversarial vulnerability in deep neural networks (DNNs) has been studied from the perspectives of decision-boundary geometry, feature robustness, input-output Jacobians, and the i…
Hybrid Surrogate Models: Circumventing Gibbs Phenomenon for Partial Differential Equations with Finite Shock-Type Discontinuities
Juan-Esteban Suarez Cardona, Shashank Reddy, Michael Hecht
We introduce the concept of Hybrid Surrogate Models (HSMs) -- combining multivariate polynomials with Heavyside functions -- as approximates of functions with finitely many jump di…
Ensuring Topological Data-Structure Preservation under Autoencoder Compression due to Latent Space Regularization in Gauss--Legendre nodes
Chethan Krishnamurthy Ramanaik, Juan-Esteban Suarez Cardona, Anna Willmann +3
We formulate a data independent latent space regularisation constraint for general unsupervised autoencoders. The regularisation rests on sampling the autoencoder Jacobian in Legen…