Markpainting: Adversarial Machine Learning meets Inpainting · HackerPapers discussions

Markpainting: Adversarial Machine Learning meets Inpainting — mentioned by dmos62

Fri, 03 Sep 2021 09:15:46 GMT

The post is pretty hard to understand. Here's the paper and an excerpt from the abstract: https://arxiv.org/abs/2106.00660 > First, we show how an image owner with access to an inpainting model can augment their image in such a way that any attempt to edit it using that model will add arbitrary visible information. We find that we can target multiple different models simultaneously with our technique. This can be designed to reconstitute a watermark if the editor had been trying to remove it. Second, we show that our markpainting technique is transferable to models that have different…

Paper and discussion history. A mention is not an endorsement.

Markpainting: Adversarial Machine Learning meets Inpainting — HN submission

Fri, 11 Jun 2021 00:32:38 GMT

Markpainting: Adversarial Machine Learning Meets Inpainting

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Markpainting: Adversarial Machine Learning meets Inpainting — HN submission

Wed, 09 Jun 2021 20:27:50 GMT

Markpainting: Adversarial Machine Learning Meets Inpainting

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.