为何AI水印难以奏效

AI companies have begun watermarking their models’ outputs to improve transparency and tackle misinformation – but the approach has limitations, reports Matthew Sparkes AS AI chatbots have taken off, you have probably found yourself wondering whether a piece of text you are reading was written by a human or a machine. Now, in response to European Union legislation, many AI firms are adding watermarks to text, images and video created by their models with the aim of letting you do just that. The hope is that these watermarks will help stem the spread of misinformation and bring transparency to the use of AI, but experts point out that, at least when it comes to text, watermarking is unlikely to work. …