GenAI Confessions: Black-box Membership Inference for Generative Image Models

TL;DR

This paper introduces a black-box membership inference method to determine if specific images were part of a generative AI model's training data, aiding in model auditing and intellectual property protection.

Contribution

The paper presents a novel, efficient black-box approach for membership inference on generative image models without requiring model architecture or weights.

Findings

Method effectively identifies training images in black-box settings

Approach is computationally efficient and architecture-agnostic

Enables auditing and fair use assessment of generative models

Abstract

From a simple text prompt, generative-AI image models can create stunningly realistic and creative images bounded, it seems, by only our imagination. These models have achieved this remarkable feat thanks, in part, to the ingestion of billions of images collected from nearly every corner of the internet. Many creators have understandably expressed concern over how their intellectual property has been ingested without their permission or a mechanism to opt out of training. As a result, questions of fair use and copyright infringement have quickly emerged. We describe a method that allows us to determine if a model was trained on a specific image or set of images. This method is computationally efficient and assumes no explicit knowledge of the model architecture or weights (so-called black-box membership inference). We anticipate that this method will be crucial for auditing existing models and, looking ahead, ensuring the fairer development and deployment of generative AI models.