Robustness of Bayesian Neural Networks to White-Box Adversarial Attacks

no code implementations • 16 Nov 2021 • Adaku Uchendu, Daniel Campoy, Christopher Menart, Alexandra Hildenbrandt

Bayesian Neural Networks (BNNs), unlike Traditional Neural Networks (TNNs) are robust and adept at handling adversarial attacks by incorporating randomness.

Adversarial Attack Bayesian Inference