What do we learn from inverting CLIP models?

Published: 12 Oct 2024, Last Modified: 14 Nov 2024SafeGenAi PosterEveryoneRevisionsBibTeXCC BY 4.0
Keywords: CLIP, NSFW, Gender Bias
Abstract: We employ an inversion-based approach to examine CLIP models. Our examination reveals that inverting CLIP models results in the generation of images that exhibit semantic alignment with the specified target prompts. We leverage these inverted images to gain insights into various aspects of CLIP models, such as their ability to blend concepts and inclusion of gender biases. We notably observe instances of NSFW (Not Safe For Work) images during model inversion. This phenomenon occurs even for semantically innocuous prompts, like `a beautiful landscape,' as well as for prompts involving the names of celebrities.
Submission Number: 9
Loading

OpenReview is a long-term project to advance science through improved peer review with legal nonprofit status. We gratefully acknowledge the support of the OpenReview Sponsors. © 2025 OpenReview