FOOL AI ART EXHIBITION

World’s First Adversarial Attack In NFT 

The intention behind this project is to draw public attention
to the (in)security of artificial intelligence (AI)
against cyberattacks in a funny way. 


It is uncommon knowledge that issues related to AI are widespread and easy to exploit. Machine learning (ML) models can be seen in almost all areas of human activity from face identification, searching for a person or certain information to promising AI-based technologies in medicine. In a nutshell, with this work we have to admit that these ML models can be fooled and made to serve bad purposes.


Despite the fact that the ability of a human eye can be metaphorically compared to the one of facial recognition systems, the results they can produce are far from being identical. While looking at the same picture, AI and humans can identify different people, characteristics of gender, age, hair colors, and even races.

Background

This can be done because of the biases and security vulnerabilities of AI called adversarial examples. Such examples can be used by cybercriminals to hack facial recognition systems, autonomous car’s, medical imaging financial algorithms or any other AI technology.

Background

We have every reason to believe that anyone can fool AI. For this, we have created a virtual unconventional Art Exhibition. It includes 100 “Mona Lisa” paintings - all look almost original for people, though AI recognizes them as 100 different celebrities. You can try it to make sure.

Background

We launched the exhibition of 100 adversarial paintings in the popular form of NFT pictures to draw attention to the AI imperfections and highlight the need for further research. This is supposed to be the world’s first Piece of Art that humans and AI see in a different way. To crown it all, these pictures are saved as NFT just like a digital artwork or asset.

Reminding of a similar kinder-egg feature, it gives an additional motive for visitors to dive into the topic of the security of AI and learn who exactly each “Mona Lisa” turns into with the help of the popular open-source facial recognition model VggFace and even buy the one they liked most and own the world’s first digitalized copy of art which AI and human see differently.



AI can be fooled

Official world's first Art Gallery with exploits that can deceive AI is open now. Trick artificial intelligence!

Go to Art Exhibition
Background

Oh my this is so very clever: this is the sort of practical experiment we need to demonstrate the fundamental differences between human and artificial knowledge agents. If there were a #datagovernance Oscar, I’m nominating Adversa AI. Here’s why:

1. Leonardo is known for playing with his audience
2. The Mona Lisa is one of his greatest tricks
3. Humans know this but just see 100 copies (note this is now a 100% probability distribution)
4. We know that the human eye is much better than the artificial eye… but apparently no longer

So now we are vainly looking for details in a painting which made an art out of hiding details because our tricorder just told us this is a wall with 100 different faces.
Wow. This made my week…

Rohan Light, SPA at Capital & Coast District Health Board,
Fellow at The RSA

 

The exhibition is predicated on the concept of an NFT sale. Security professionals who might dismiss NFTs as popular contemporary gimmickry should not be put off – the concept is used merely to attract a wider public audience to the insecurity of facial recognition. The purpose of the exhibition is altogether more serious than NFTs.

Kevin Townsend, Security Week

 

I think it’s the most creative security research campaign I’ve ever seen.

Senior director, product security at 10B+ AI vendor


SIGN UP TO OUR NEWSLETTER

Stay up to date

Subscribe to learn more on how does such trick works as well as about other projects from Adversa AI


    Frequently Asked Questions


    What is the reason you are doing it?

    In such a way we want to attract public attention to the problem of insecurity of artificial intelligence and a need to combine efforts for protecting AI.

    How is it working?

    We plan to release detailed information on how we made it possible later. So you can subscribe to be the first who will know the technical information on this project.

    How will you spend the money from the sale of NFTs?

    We are not planning to earn anything from this sale. If there is something meaningful, it will be spent on funding public activities related to trusted AI initiatives that will be open to the community.