← Search

Ginevra Carbone

2 accepted papers

2025

Zero-Shot Conditioning of Score-Based Diffusion Models by Neuro-Symbolic Constraints

AAAI 2025technical

Score-based diffusion models have emerged as effective approaches for both conditional and unconditional generation. Still conditional generation is based on either a specific training of a conditional model or classifier guidance, which requires training a noise-dependent classifier, even when a c…

2020

Robustness of Bayesian Neural Networks to Gradient-Based Attacks

NeurIPS 2020poster

Vulnerability to adversarial attacks is one of the principal hurdles to the adoption of deep learning in safety-critical applications. Despite significant efforts, both practical and theoretical, the problem remains open. In this paper, we analyse the geometry of adversarial attacks in the large-dat…