ARIA: Adversarially Robust Image Attribution for Content Provenance. (arXiv:2202.12860v1 [cs.CV])

Image attribution -- matching an image back to a trusted source -- is an
emerging tool in the fight against online misinformation. Deep visual
fingerprinting models have recently been explored for this purpose. However,
they are not robust to tiny input perturbations known as adversarial examples.
First we illustrate how to generate valid adversarial images that can easily
cause incorrect image attribution. Then we describe an approach to prevent
imperceptible adversarial attacks on deep visual fingerprinting models, via
robust contrastive …

arxiv attribution cv image provenance