Shulou(Shulou.com)11/24 Report--

Thanks to CTOnews.com netizen OC_Formula for the clue delivery! CTOnews.com, October 6, according to foreign media Engadget, Wired and other reports, a research team from the University of Maryland in the United States studied the reliability of the "digital watermarking" technology for content generated by AI and found that this technology can be easily cracked.

Soheil Feizi, a professor of computer science at the university, said bluntly about the current situation of watermarking generated by AI: "at present, we do not have any reliable watermarking technology, we have cracked all the watermarks."

In the course of testing, researchers can easily avoid existing watermarking methods and find it easier to add "fake watermarks" to non-AI-generated images. At the same time, the team has also developed a watermarking technology that is "almost impossible" to remove from the image without completely damaging the intellectual property of the image.

In a similar study by the University of California, Santa Barbara and Carnegie Mellon University, researchers found that watermarks in AI-generated images can be easily removed by "simulated attacks": by damaging adjustments to brightness, contrast or compression or even rotating the image, or by constructive Gaussian blur techniques.

It is reported that the generation of digital watermarks by AI will become a competition with hackers. Although invisible to the naked eye, this kind of watermark can combat the misuse of AI-generated content.

CTOnews.com previously reported that the US government announced in late July that it had received voluntary commitments from several AI head companies to add watermarks and other measures to help improve the security of the technology.

Amazon, Anthropic, Google, Inflection, Meta, Microsoft and OpenAI all agreed to improve the security and transparency of their systems, including allowing third-party experts to review their models.

In a statement to the TechRadar, the US government said: "companies developing these emerging technologies have a responsibility to ensure the safety of their products. In order to realize the full potential of artificial intelligence, the US government encourages the industry to adhere to the highest standards to ensure that innovation does not come at the expense of the rights and security of Americans."

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.