flâneur

Detecting AI fingerprints: A guide to watermarking and beyond

brookings.edu · 8,318 words · saved by 1 readers

Over the last year, generative AI tools have made the jump from research prototype to commercial product. Generative AI models like OpenAI’s ChatGPT and Google’s Gemini can now generate realistic text and images that are often indistinguishable from human-authored content, with generative AI for audio and video not far behind. Given these advances, it’s no longer surprising to see AI-generated images of public figures go viral 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. Against the backdrop of such technological advances, civil society and policymakers have taken increasing interest in ways to distinguish AI-generated content from human-authored content. The EU AI Act contains provisions that require users of AI systems in certain contexts to disclose and label their AI-generated content, as well as provisions that require p

Research Siddarth Srinivasan Siddarth Srinivasan Postdoctoral Fellow - Harvard University January 4, 2024 Key takeaways Sophisticated digital “watermarking” embeds subtle patterns in AI-generated content that only computers can detect. Relative to other approaches to identifying AI-generated content, watermarks are accurate and more robust to erasure and forgery, but they are not foolproof; a motivated actor can degrade watermarks in AI-generated content. An AI model developer can only build detectors for their own watermark, so coordination will be necessary for efficient…

related reading