Skip to main content

“We broke them all” — How researchers broke current image watermarking protections and what it means for a new era of truth-altering ‘reality’

The tool many big tech companies are banking heavily on being able to help the public and businesses separate fact from fiction, in the context of AI’s meteoric rise, has already been undermined before it’s even taken off.

The idea of watermarking is something that companies including OpenAI, Amazon and Google have pointed to as being able to combat disinformation online. With generative AI on the rise, particularly in the form of deepfakes, it might be looked at as one way to identify what’s actually real. It’s one of the key proposals among efforts to make the usage of AI, safer and more transparent.

There aren’t, however, many clear-cut approaches to watermarking yet that are completely fool-proof or reliable, and professors with the University of Maryland have already found a way to break all of the existing methods, according to TechXplore.

How scientists have already cracked AI watermarking

The researchers used a technique called diffusion purification to blast Gaussian noise – a kind of electronic noise signaling – at a watermark to completely remove it, without impacting the underlying image too much. 

With AI-generated content on the rise, especially in certain industries, the scope for abuse has also surfaced as a very real possibility. It’s also essential to find tools and strategies to be able to distinguish genuine content from that made by machines.

Watermarking is a promising approach, according to the paper, published on 29 September. It involves hiding a signal in a piece of text or image to determine if it’s AI-generated. The theory goes a tool you run the content through would then be able to determine whether it’s real or fake, and avoid the prospect of falling for something that isn’t real. But the attack method – diffusion purification – has already been able to nullify today’s watermarks.

“Based on our results, designing a robust watermark is a challenging, but not necessarily impossible task,” the paper said, offering a glimmer of hope.

“An effective method should possess specific attributes, including a substantial enough watermark perturbation, resistance to naive classification, and resilience to noise transferred from other watermarked images.”

More from TechRadar Pro



Comments

Post a Comment

Popular posts from this blog

The latest Apple TV 4K test lets you watch four sports streams at once

Apple is trying something new with the latest beta version of tvOS 16.5: the option to watch up to four simultaneous streams at once. Right now it's limited to live sports streamed through the Apple TV app on the Apple TV 4K , specifically MLB Friday Night Baseball and the MLS Season Pass. A multi-view option was spotted in the tvOS software last month, but the code was hidden and not enabled. MacRumors reported that the feature would be enabled this weekend, and beta testers have since been able to use it. As yet multi-view hasn't been officially announced by Apple, but it's expected that tvOS 16.5 is going to be pushed out in its final form within the next month or so. WWDC 2023 is around the corner as well, when we should be hearing about the next major updates for Apple's various operating systems – including tvOS 17. How it works Over at 9to5Mac there's a hands-on demonstrating how the multi-view feature works, and it's pretty much as you would expe...
Post a Comment
Read more

Quantum computers are fast becoming cheaper and smaller — and they could be coming to a data center near you very soon

IonQ claims we’re closer to widespread enterprise quantum computing deployment as it lifted the lid on two rack-mounted models that can be deployed on-premises.   The startup has built the fourth-generation #AQ35 IonQ Forte Enterprise and fifth-generation #AQ64 IonQ Tempo, both of which are designed to be deployed in enterprise and government data centers. It’s also said it is deploying two quantum computers to the US Air Force.  While revealing these two models, IonQ co-founder and CTO Jungsang Kim said quantum computers are already in use by enterprises to churn through machine learning workloads. This, he added, suggests we’re much closer to readily available and affordable machines. Priming enterprises for a quantum future “We believe in the enterprise-grade quantum computing, which is where it can be something of value for enterprises, can happen in the next few years as we build powerful enough quantum computers that can actually do things that classical computers w...
Post a Comment
Read more

Nvidia RTX 4080 GPU could get cheaper with a new version – but don’t get your hopes up

Nvidia’s RTX 4080 is purportedly getting a new spin on the GPU which could reduce the cost, but any price reduction will likely be very minor, sadly, if it happens at all. Tom’s Hardware flagged up this rumor – and treat it with caution, as with anything from the ever-spinning mill – that originated from HKEPC (a tech site in Hong Kong), claiming that while the current RTX 4080 graphics card is built on the AD103-300 chip, Nvidia is going to use a slightly different GPU in the future, namely AD103-301. There’s now more evidence this is actually happening, Tom’s points out, courtesy of a graphics card maker, Galax, which under its RTX 4080 product details lists the GPU as ‘AD103-300/301’. Furthermore, VideoCardz , which also picked up on this, informs us that Gainward, another card maker, has also listed the updated GPU variant AD103-301 in its product specs. With two separate third-party graphics card makers mentioning this new spin on the GPU in their specs, it seems pret...
Post a Comment
Read more