The Austrian newspaper “Der Standard” published an article about Katharina in their research section. In the article, Katharina also talks about P3F as one of her exciting research projects.
Yesterday, we visited the netidee spring talk to present the progress of our project. The subsequent discussion was very fruitful and our brand-new privacy T-shirt collection received a lot of attention.
(photo credits: netidee)
We are happy to announce that we received a follow-up funding to port the P3F framework to Google Glass!! We are so excited to play around with Google Glass and to the upcoming challences that this new technology implies!
As Adrian is still in Tokyo, he unfortunately couldn’t join this picture from the netidee best-of ceremony. Of course we will celebrate as soon as returns 🙂
It’s summer, imagine you are on holidays in Bali. The weather is perfect, the water is clear and the sand not too hot to walk on. You want to enjoy the beach so you put on your red bikini. Now you are standing in the sand, nearby are other tourists having fun. One of them as a camera and makes snapshots of his friends. Unfortunately you are not too far away from them and appear on almost every picture, but you don’t know that. Suddenly you pay attention to the photographer and realize that you may be on some of the pictures he just took. Oh noes! You are in a very uncomfortable situation and too shy to ask the photographer to show you the pictures he just made and maybe erase the ones you don’t like. Luckily you are wearing the red P3F bikini and thanks god, the photographer uses the P3F framework to check his images for privacy policies encoded in the swimwear of the people he just recorded!
His P3F framework is just a prototype version developed in Matlab. Matlab is a great platform to develop things like that – it has cool toolboxes that make image processing easy and fun.
The core components of our Matlab implementation are:
- Preprocessor: pre-processes the image to remove distortions e.g. caused by illumination
- Face Detector: detects faces in the image
- Artefact Detector: detects P3F artefacts on people inside the image
We are currently working on a comprehensive document that describes the components in detail. We are also working on a new, enhanced version that supports more complex patterns. We are also improving face detection and body segmentation to minimize false positives.
A new gadget joined the P3F team. We are finally proud owners of the Google Glass Explorer version. 🙂
Besides playing around and exploring the Glass API, we are currently working on a proposal to apply for a netidee follow-up grant. We would really like to take P3F to the next level and include Glass feature.
Wearable such as Glass are exciting – but preserving bystanders’ privacy is challenging!
Last week, I visited SOUPS (Symposium on Usable Privacy and Security) in Menlo Park, CA, USA at the Facebook HQ. Besides listening to many interesting talks, I had the chance to meet researchers from all over the world to exchange ideas and to spread the word about P3F.
According to a news article by Gizmodo Google has formally announced that it’s opening sales of Google Glass to everyone in the U.S. Even though the price ($1,500) will still detain some potential costumers from buying this promising new device, the permanent video record of humans in public spaces is a potential scenario that we will encounter in the next years. Google Glass therefore has several privacy implications on the people that are recorded by these devices.
This development highlights the need for privacy enhancing techniques that are reliable and easy to use. The P3F framework has the ability to provide such a usable and efficient countermeasure against contiuous video recording and mass surveillance.
After evaluating the algorithms to be used in the P3F framework, we defined the general architecture of our framework and started with the prototype implementation in Matlab.
The overall goal is to modify an input image in a way so all persons on the respective image are presented as defined by their privacy policies. The first step consists of preprocessing (i.e. removal of distortions, calculation of integral/greyscale images, …). After preprocessing the image is segmented. In the P3F framework, image segmentation is performed by a face locator, a person locator and a data locator and decoder to obain a list of persons and tags. From these lists, the privacy policies are deducted and furthermore enforced.