ginevracoal/robustBNNs

Stars
16
Rank 1,311,288 (Top 26 %)
Language
Python
Created over 4 years ago
Updated 9 months ago

ginevracoal/robustBNNs

ginevracoal

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Code for paper "Robustness of Bayesian Neural Networks to Gradient-Based Attacks"

statistical-machine-learning

Probabilistic Machine Learning course lab @UNITS

Jupyter Notebook

smoothed-model-checking

Code for paper "Stochastic Variational Smoothed Model Checking", Luca Bortolussi, Francesca Cairoli, Ginevra Carbone, Paolo Pulcini (2022)

redbnn

Reduced Bayesian Neural Networks are Deterministic Neural Networks with a Bayesian subset of weights. redBNN class computes a MAP estimate of the entire NN and then performs Bayesian inference on a chosen layer or block.

adversarial_examples

Random Projections for improved Adversarial Robustness

Jupyter Notebook

adversarial-protein-sequences

Code for paper "Adversarial Attacks on Protein Language Models", Ginevra Carbone, Francesca Cuturello, Luca Bortolussi, Alberto Cazzaniga (2022).

GAN-abstraction

statisticalMachineLearning

repo for the course of DSSC "Statistical Machine Learning"

Jupyter Notebook

large-scale-kernel-approximation

BayesianRelevance

Code for paper "Resilience of Bayesian Layer-Wise Explanations under Adversarial Attacks", Ginevra Carbone, Guido Sanguinetti, Luca Bortolussi, 2021