News on May 24, as more and more "deep fake" images and videos appear, Microsoft has decided to take proactive measures to ensure that its program-generated AI art can be recognized. At the Microsoft Build 2023 developer conference, the company announced that it will add a feature in the coming months that will allow anyone to identify whether images or video clips generated by Bing Image Creator and Microsoft Designer were generated by AI. Microsoft claims that their technology uses cryptography to identify and sign AI-generated content, and attaches source data information to indicate its origin.
Other companies are also taking active actions and expressing their opinions on digital watermarking, not just Microsoft, such as Douyin, Google and OpenAI. The identification information can be directly embedded in the digital carrier without affecting the function of the original carrier, and it is not easy to detect and modify again. Digital watermarks can be identified and identified by the producer. Through the information hidden in the carrier, the purpose of identifying the content creator and purchaser, transmitting secret information, or determining whether the carrier has been tampered with can be achieved.
Among A-share companies, Hengxin Oriental (300081) has mature digital watermarking technology, which has been used in AI family entertainment platform application products and VR product-related materials. Beixinyuan (300352) and Baidu will carry out more in-depth cooperation in various fields such as digital watermarking, including product research and development and standard formulation. At present, the company's watermark system covers two major categories: clear watermarks and hidden watermarks.
The above is the detailed content of Microsoft will provide developers with AI digital watermarking tools. For more information, please follow other related articles on the PHP Chinese website!