1 citations · 1 across the 4 of their papers we have counts for
5 papers
Frame the adversary: a structure-aware attack methodology
Vicky Kouni, Stelios Perrakis, Francis Bach +2
Frequency-based adversarial attacks have recently grown popular by exploiting spectral sensitivities shared across neural architectures. Unlike spatial perturbations, frequency-bas…
A Robust Optimization Approach to Sparse Principal Component Analysis
David Vävinggren, Francis Bach, André M. H. Teixeira +2
While principal component analysis (PCA) is a fundamental tool for dimensionality reduction, its dense representations make it ill-suited for high-dimensional data. Existing method…
Kernel Learning with Adversarial Features: Numerical Efficiency and Adaptive Regularization
Antônio H. Ribeiro, David Vävinggren, Dave Zachariah +2
Adversarial training has emerged as a key technique to enhance model robustness against adversarial input perturbations. Many of the existing methods rely on computationally expens…
Efficient Optimization Algorithms for Linear Adversarial Training
Antônio H. RIbeiro, Thomas B. Schön, Dave Zahariah +1
Adversarial training can be used to learn models that are robust against perturbations. For linear models, it can be formulated as a convex optimization problem. Compared to method…
Regularization properties of adversarially-trained linear regression
Antônio H. Ribeiro, Dave Zachariah, Francis Bach +1
State-of-the-art machine learning models can be vulnerable to very small input perturbations that are adversarially constructed. Adversarial training is an effective approach to de…