The article introduces algorithms PIE and GIE for computing tight guarantees on the probabilistic robustness of Bayesian Neural Networks (BNNs). It highlights the challenges in verifying BNNs compared to standard NNs and the limitations of existing approaches. The algorithms efficiently search for safe weights using iterative expansion and network gradients, outperforming the state-of-the-art (SoA) in terms of tightness of bounds. Evaluation on MNIST and CIFAR10 datasets shows significant improvements in bounds.
To Another Language
from source content
arxiv.org
Ключові висновки, отримані з
by Ben Batten,M... о arxiv.org 03-01-2024
https://arxiv.org/pdf/2401.11627.pdfГлибші Запити