CommunityNews

CommunityNews

Detecting Deepfake Picture Editing

“Markpainting” is a clever technique to watermark photos in such a way that makes it easier to detect ML-based manipulation:

An image owner can modify their image in subtle ways which are not themselves very visible, but will sabotage any attempt to inpaint it by adding visible information determined in advance by the markpainter.

One application is tamper-resistant marks. For example, a photo agency that makes stock photos available on its website with copyright watermarks can markpaint them in such a way that anyone using common editing software to remove a watermark will fail; the copyright mark will be markpainted right back. So watermarks can be made a lot more robust.

Here’s the paper: “Markpainting: Adversarial Machine Learning Meets Inpainting,” by David Khachaturov, Ilia Shumailov, Yiren Zhao, Nicolas Papernot, and Ross Anderson.

Read in full here:

https://www.schneier.com/blog/archives/2021/06/detecting-deepfake-picture-editing.html

This thread was posted by one of our members via one of our news source trackers.

First Post!

AstonJ

AstonJ

Hadn’t heard of ‘Markpainting’ before - definitely going to look into it more as people stealing pics is such a nuisance! If anyone has any experience please share :smiley:

From the link in the first paragraph:

Common graphics software now offers powerful tools for inpainting – using machine-learning models to reconstruct missing pieces of an image. They are widely used for picture editing and retouching, but like many sophisticated tools they can also be abused. They can remove someone from a picture of a crime scene, or remove a watermark from a stock photo. Could we make such abuses more difficult?

We introduce Markpainting, which uses adversarial machine-learning techniques to fool the inpainter into making its edits evident to the naked eye. An image owner can modify their image in subtle ways which are not themselves very visible, but will sabotage any attempt to inpaint it by adding visible information determined in advance by the markpainter.

One application is tamper-resistant marks. For example, a photo agency that makes stock photos available on its website with copyright watermarks can markpaint them in such a way that anyone using common editing software to remove a watermark will fail; the copyright mark will be markpainted right back. So watermarks can be made a lot more robust.

In the fight against fake news, markpainting news photos would mean that anyone trying to manipulate them would risk visible artefacts. So bad actors would have to check and retouch photos manually, rather than trying use inpainting tools to automate forgery at scale.

This paper has been accepted at ICML.

Where Next?

Popular Other Fields topics Top

AstonJ
China used facial recognition quite extensively: And now Russia is too: https://www.bbc.co.uk/news/av/world-europe-52157131/coronaviru...
New
PragmaticBookshelf
Self-driving cars, natural language recognition, and online recommendation engines are all possible thanks to Machine Learning. Discover...
New
AstonJ
Is this the future of photography - or spying even :joy: Creating realistic 3D photo-models from a series of photographs - in this case ...
New
CommunityNews
Data. It’s everywhere and we’re only getting more of it. For the last 5-10 years, data science has attracted newcomers near and far tryin...
New
First poster: bot
We introduce the problem of perpetual view generation —long-range generation of novel views corresponding to an arbitrarily long camera t...
New
First poster: davearonson
Deep learning may transform health care, but model development has largely been dependent on availability of advanced technical expertise...
New
CommunityNews
“Markpainting” is a clever technique to watermark photos in such a way that makes it easier to detect ML-based manipulation: An image o...
New
First poster: bot
The Modern Mathematics of Deep Learning. We describe the new field of mathematical analysis of deep learning. This field emerged around...
New
First poster: bot
Two recent collaborations between mathematicians and DeepMind demonstrate the potential of machine learning to help researchers generate ...
New
ManningBooks
The book focuses on designing a complete, modular lakehouse architecture using Apache Iceberg—leveraging open source tools instead of rel...
New

Other popular topics Top

Rainer
My first contact with Erlang was about 2 years ago when I used RabbitMQ, which is written in Erlang, for my job. This made me curious and...
New
AstonJ
I ended up cancelling my Moonlander order as I think it’s just going to be a bit too bulky for me. I think the Planck and the Preonic (o...
New
Rainer
Not sure if following fits exactly this thread, or if we should have a hobby thread… For many years I’m designing and building model air...
New
PragmaticBookshelf
Learn different ways of writing concurrent code in Elixir and increase your application's performance, without sacrificing scalability or...
New
mafinar
Crystal recently reached version 1. I had been following it for awhile but never got to really learn it. Most languages I picked up out o...
New
PragmaticBookshelf
Create efficient, elegant software tests in pytest, Python's most powerful testing framework. Brian Okken @brianokken Edited by Kat...
New
AstonJ
Saw this on TikTok of all places! :lol: Anyone heard of them before? Lite:
New
PragmaticBookshelf
Author Spotlight: Tammy Coron @Paradox927 Gaming, and writing games in particular, is about passion, vision, experience, and immersio...
New
AstonJ
If you’re getting errors like this: psql: error: connection to server on socket “/tmp/.s.PGSQL.5432” failed: No such file or directory ...
New
AstonJ
Curious what kind of results others are getting, I think actually prefer the 7B model to the 32B model, not only is it faster but the qua...
New