Detecting AI Fingerprints: A Guide to Watermarking and Beyond

By Srinivasan, Siddarth

From the document: "Over the last year, generative AI [artificial intelligence] tools have made the jump from research prototype to commercial product. Generative AI models like OpenAI's ChatGPT [Chat Generative Pre-trained Transformer] [hyperlink] and Google's Gemini [hyperlink] can now generate realistic text and images that are often indistinguishable from human-authored content, with generative AI for audio [hyperlink] and video [hyperlink] not far behind. Given these advances, it's no longer surprising to see AI-generated images of public figures go viral [hyperlink] or AI-generated reviews and comments on digital platforms. As such, generative AI models are raising concerns about the credibility of digital content and the ease of producing harmful content going forward. [...] There are several ideas for how to tell whether a given piece of content--be it text, image, audio, or video--originates from a machine or a human. This report explores what makes for a good AI detection tool, how the oft-touted approach of 'watermarking' fares on various technical and policy-relevant criteria, governance of watermarking protocols, what policy objectives need to be met to promote watermark-based AI detection, and how watermarking stacks up against other suggested approaches like content provenance."

Washington. DC. Brookings Institution. 2024.