Adversarial Robustness is at Odds with Lazy Training. (arXiv:2207.00411v1 [cs.CR])

Recent works show that random neural networks are vulnerable against
adversarial attacks [Daniely and Schacham, 2020] and that such attacks can be
easily found using a single step of gradient descent [Bubeck et al., 2021]. In
this work, we take it one step further and show that a single gradient step can
find adversarial examples for networks trained in the so-called lazy regime.
This regime is interesting because even though the neural network weights
remain close to the initialization, there …

adversarial robustness training