Generative AI has revolutionised visual content editing, empowering users to effortlessly modify images and videos. However, not all edits are equal. To perform realistic edits in domains such as natural image or medical imaging, modifications must respect causal relationships inherent to the data generation process.

An adversary may be able to "steal" the model by querying for counterfactuals and training a

We next discuss two lines of related literature.

Counterfactual Fairness (CF), which posits that an ML model's outcome on any individual should remain unchanged if they had belonged to a different demographic

Typically,givenanindividual,atreatmentassignment,andatreatmentoutcome, the counterfactual question asks what would have happened to that individual, had it been given anothertreatment,everythingelsebeingequal.