Google has released its watermarking artificial intelligence, or AI, text tool.
The technology giant’s SynthID is a tool developed by Google DeepMind, the firm’s AI laboratory.
“SynthID is a technology from Google DeepMind that watermarks and identifies AI-generated content by embedding digital watermarks directly into AI-generated images, audio, text or video. SynthID Text has been open-sourced to make watermarking for text generation available to developers,” the tech giant wrote in a post on its blog dedicated to developers.
MIT Technology Review states watermarking works by “inserting hidden patterns in AI-generated text, which allow computers to detect that the text comes from an AI system.”
Even though it has become the go-to solution for preventing AI-generated misinformation and plagiarism, Google states in the blog post the algorithm is currently on Gemini and Gemini Advance because “there is concern that it could contribute to misinformation and misattribution problems.”
It added that SynthID Text is “not designed to directly stop motivated adversaries from causing harm. However, it can make it harder to use AI-generated content for malicious purposes, and it can be combined with other approaches to give better coverage across content types and platforms.”
It is, however, robust when “cropping pieces of text, modifying a few words or mild paraphrasing.”
