Constructing Semantics-Aware Adversarial Examples with Probabilistic Perspective

We propose a probabilistic perspective on adversarial examples. This perspective allows us to view geometric restrictions on adversarial examples as distributions, enabling a seamless shift towards data-driven, semantic constraints. Building on this foundation, we present a method for creating semantics-aware adversarial examples in a principle way. Leveraging the advanced generalization capabilities of contemporary probabilistic generative models, our method produces adversarial perturbations that maintain the original image's semantics. Moreover, it offers users the flexibility to inject their own understanding of semantics …

advanced adversarial aware building capabilities constraints cs.cr cs.lg data data-driven distributions examples foundation perspective restrictions semantic stat.ml