Timezone: »

 
Black Box Adversarial Prompting for Foundation Models
Natalie Maus · Patrick Chao · Eric Wong · Jacob Gardner
Event URL: https://openreview.net/forum?id=aI5QPjTRbS »

Prompting interfaces allow users to quickly adjust the output of generative models in both vision and language. However, small changes and design choices in the prompt can lead to significant differences in the output. In this work, we develop a black-box framework for generating adversarial prompts for unstructured image and text generation. These prompts, which can be standalone or prepended to benign prompts, induce specific behaviors into the generative process, such as generating images of a particular object or generating high perplexity text.

Author Information

Natalie Maus (University of Pennsylvania)
Patrick Chao (University of Pennsylvania)
Eric Wong (University of Pennsylvania)
Jacob Gardner (University of Pennsylvania)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors