Soheil Feizi, a professor of computer science at the school, was blunt when faced with the current status of watermarks in AI-generated images: “Currently we do not have any reliable watermark technology, and we have cracked all watermarks.”

During testing, the researchers were able to easily circumvent existing watermarking methods and found it easier to add “fake watermarks” to non-AI-generated images. At the same time, the team has also developed a watermark technology that is “almost impossible” to remove from images without completely compromising the image’s intellectual property.

In a similar study by the University of California, Santa Barbara and Carnegie Mellon University, researchers found that watermarks on AI-generated images can be easily removed through “simulation attacks”: by destructively adjusting brightness and contrast. Either compress or even rotate the image to remove it, or remove it through techniques such as constructive Gaussian blur.

According to reports, AI-generated digital watermarks will become a competition with hackers. This watermark, although invisible to the naked eye, can combat misuse of AI-generated content.

It was previously reported that the U.S. government announced in late July that it had obtained voluntary commitments from a number of leading artificial intelligence companies to add watermarks to content generated by artificial intelligence and other measures to help improve the security of the technology.

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

In a statement to TechRadar, the U.S. government said: “Companies that are developing these emerging technologies have a responsibility to ensure the safety of their products. To realize the full potential of artificial intelligence, the U.S. government encourages the industry to adhere to the highest standards to ensure innovation Not at the expense of the rights and safety of Americans.”

The post Study shows digital watermarks added to AI-generated images can be easily cracked appeared first on TechGoing.

The principle of SynthID is to embed a watermark in the pixels of the image without affecting the quality and experience of the image itself. The watermark can resist common image editing operations such as cropping and scaling, and can only be identified by specialized AI detection tools. Demis Hassabis, CEO of Google DeepMind, said that this watermark will become more subtle and powerful as the AI model improves.

SynthID tool tells you how likely it is that an image is AI-generated

Hassabis said SynthID was developed to address potentially dangerous issues such as deepfakes. He believes that the establishment of AI image recognition systems is very important in the context of the upcoming general elections in the United States and the United Kingdom in 2024. He also said that the basic idea of SynthID can also be applied to other media such as video and text.

Currently, SynthID is only available on Google Cloud Platform, primarily for customers using the Vertex AI platform and Imagen image generator. Hassabis hopes to make SynthID better by testing in real scenarios. Google will then use it in more places, share it with more partners, and increase public awareness and education.

It is noticed that in addition to Google, many other companies are also working on building AI protection and security systems. For example, companies like Meta, OpenAI, and others are using a protocol called C2PA to tag AI-generated content with encrypted metadata. Hassabis said that SynthID may become one of the Internet-wide standards. But he also emphasized that this is only an initial attempt and is not a panacea for solving the problem of deepfakes. “It’s too early to think about scaling and social discussions until we’ve proven that the technology fundamentals work in part,” he said.

The post DeepMind’s SynthID tool embeds invisible watermarks in AI-generated images appeared first on TechGoing.

However, there is also concern that AI-generated artwork could be used maliciously to spread false information. As more and more “deep-fake” images and videos emerge, Microsoft has decided to take proactive steps to ensure that its program-generated AI art can be identified. Today, 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 are generated by AI.

The technology uses cryptographic methods to tag and sign AI-generated content with metadata information about its origin,” Microsoft said. Microsoft has been a leader in the development of provenance verification methods and co-founded Project Origin and the Content Origin and Authenticity Alliance (C2PA) standards body. Microsoft’s media provenance verification will sign and validate generated content in accordance with C2PA standards.”

Microsoft announced earlier this month that Bing Image Creator now supports more than 100 languages and that the program has created more than 200 million images.

The post Microsoft cracks down on deep fakes, adding ‘ID’ to AI-generated images and videos appeared first on TechGoing.