Adversarial Attacks on Image Generation With Made-Up Words. (arXiv:2208.04135v1 [cs.CV])

Text-guided image generation models can be prompted to generate images using
nonce words adversarially designed to robustly evoke specific visual concepts.
Two approaches for such generation are introduced: macaronic prompting, which
involves designing cryptic hybrid words by concatenating subword units from
different languages; and evocative prompting, which involves designing nonce
words whose broad morphological features are similar enough to that of existing
words to trigger robust visual associations. The two methods can also be
combined to generate images associated with …

adversarial attacks image generation