Constructing Semantics-Aware Adversarial Examples with Probabilistic Perspective. (arXiv:2306.00353v1 [stat.ML])

In this study, we introduce a novel, probabilistic viewpoint on adversarial
examples, achieved through box-constrained Langevin Monte Carlo (LMC).
Proceeding from this perspective, we develop an innovative approach for
generating semantics-aware adversarial examples in a principled manner. This
methodology transcends the restriction imposed by geometric distance, instead
opting for semantic constraints. Our approach empowers individuals to
incorporate their personal comprehension of semantics into the model. Through
human evaluation, we validate that our semantics-aware adversarial examples
maintain their inherent meaning. Experimental …

adversarial aware box constraints monte carlo novel perspective study