Finding needles in a haystack: A Black-Box Approach to Invisible Watermark Detection
This provides a versatile solution for increasing accountability and transparency in digital visual content, addressing a growing need as invisible watermarks become more common.
The paper tackles the problem of detecting invisible watermarks in images without prior knowledge of the watermarking techniques, using a black-box and annotation-free approach, and achieves AUC scores over 0.9 for single-watermark datasets and over 0.7 for multi-watermark scenarios.
In this paper, we propose WaterMark Detection (WMD), the first invisible watermark detection method under a black-box and annotation-free setting. WMD is capable of detecting arbitrary watermarks within a given reference dataset using a clean non-watermarked dataset as a reference, without relying on specific decoding methods or prior knowledge of the watermarking techniques. We develop WMD using foundations of offset learning, where a clean non-watermarked dataset enables us to isolate the influence of only watermarked samples in the reference dataset. Our comprehensive evaluations demonstrate the effectiveness of WMD, significantly outperforming naive detection methods, which only yield AUC scores around 0.5. In contrast, WMD consistently achieves impressive detection AUC scores, surpassing 0.9 in most single-watermark datasets and exceeding 0.7 in more challenging multi-watermark scenarios across diverse datasets and watermarking methods. As invisible watermarks become increasingly prevalent, while specific decoding techniques remain undisclosed, our approach provides a versatile solution and establishes a path toward increasing accountability, transparency, and trust in our digital visual content.