GenAI Confessions: Black-box Membership Inference for Generative Image Models
This addresses concerns over intellectual property and copyright infringement for creators affected by unauthorized use of their images in AI training, though it is incremental as it builds on existing membership inference techniques.
The paper tackles the problem of determining whether generative image models were trained on specific images without permission, by developing a computationally efficient black-box membership inference method that requires no knowledge of model architecture or weights.
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.