Enhancing Adversarial Robustness via Score-Based Optimization. (arXiv:2307.04333v2 [cs.LG] UPDATED)

Adversarial attacks have the potential to mislead deep neural network
classifiers by introducing slight perturbations. Developing algorithms that can
mitigate the effects of these attacks is crucial for ensuring the safe use of
artificial intelligence. Recent studies have suggested that score-based
diffusion models are effective in adversarial defenses. However, existing
diffusion-based defenses rely on the sequential simulation of the reversed
stochastic differential equations of diffusion models, which are
computationally inefficient and yield suboptimal results. In this paper, we
introduce a …

adversarial adversarial attacks algorithms artificial artificial intelligence attacks diffusion models intelligence network neural network optimization robustness safe score studies