2 papers
cs.LG2026
Solving adversarial examples requires solving exponential misalignment
Alessandro Salvatore, Stanislav Fort, Surya Ganguli
Adversarial attacks - input perturbations imperceptible to humans that fool neural networks - remain both a persistent failure mode in machine learning, and a phenomenon with myste…
cond-mat.stat-mech2025
Patterns robust to Disorder in spatially-interacting Generalized Lotka-Volterra Ecosystems
Alessandro Salvatore, Fabián Aguirre-López, Ruben Zakine
How do interactions between species influence their spatial distribution in an ecosystem? To answer this question, we introduce a spatially-extended ecosystem of Generalized Lotka-…