Semantically Stealthy Adversarial Attacks against Segmentation Models. (arXiv:2104.01732v3 [cs.CV] UPDATED)

Segmentation models have been found to be vulnerable to targeted and
non-targeted adversarial attacks. However, the resulting segmentation outputs
are often so damaged that it is easy to spot an attack. In this paper, we
propose semantically stealthy adversarial attacks which can manipulate targeted
labels while preserving non-targeted labels at the same time. One challenge is
making semantically meaningful manipulations across datasets and models.
Another challenge is avoiding damaging non-targeted labels. To solve these
challenges, we consider each input image …

arxiv attacks cv segmentation