The Effectiveness of the Meta-Detection for Countering Oracle Attacks in Watermarking

We evaluate the performance of smart metadetection as a way to combact oracle attacks in watermarking. In a recent work, we have shown that few queries are sufficient for a simple metadetector (namely a meta-detector based on the closeness of queries to the watermark detection boundary) to detect an oracle attack. A limitation of our prior analysis is the assumption that all the queries correspond to either honest users or malicious ones. In this paper, we address a more realistic scenario in which honest queries are interspersed with queries derived from an oracle-attack. By focusing on this more general situation, we evaluate the performance of the metadetection and derive conditions under which powerful testing is possible.