← Search

Ramchandran Muthukumar

2 accepted papers

2025

Disentangling Safe and Unsafe Image Corruptions via Anisotropy and Locality

CVPR 2025poster

State-of-the-art machine learning systems are vulnerable to small perturbations to their input, where _small_ is defined according to a threat model that assigns a positive threat to each perturbation. Most prior works define a task-agnostic, isotropic, and global threat, like the l_p norm, where th…

Cited by 0SourcePDFScholar
2020

Adversarial Robustness of Supervised Sparse Coding

NeurIPS 2020poster

Several recent results provide theoretical insights into the phenomena of adversarial examples. Existing results, however, are often limited due to a gap between the simplicity of the models studied and the complexity of those deployed in practice. In this work, we strike a better balance by conside…