Eyeo, the company behind Adblock Plus, wants to enlist Facebook user’s help in building their next advertisement blocking application, which will be constructed using machine learning techniques.
Eyeo today launched the website adblock.ai where they encourage users to send in snapshots of their Facebook feeds.
The computational brain behind the work is called Sentinel, a neural network which once trained is hoped will be able to detect advertisements without using blocking and filter lists which is how the technology currently works.
They named it Sentinel, in their own words on the site: “Because we thought that it sounds awesome and fearsome”.
Speaking to Computer Business Review, Ben Williams Director of Ecosystems for Adblock Plus said that: “One big long term goal of this is to forever end company’s circumvention efforts.”
Eyeo co-founder Till Faida added in an emailed statement: “Facebook and others are getting clever at disguising ads from ad blockers and using circumvention techniques to show you ads anyway.”
He added that: “These tricks disregard your stated preference to block ads. We’ve always been able to develop workarounds to these circumvention techniques, but this cat-and-mouse game will likely continue for the foreseeable future.”
If you want you’re paid for advertisements to be seen by people using Eyeo’s Ad Blocker Plus you can pay them to have your content whitelisted. This enables those using the blocker on its less harsh settings to see those advertisements.
Williams informed Computer Business Review that the project was spearheaded by one engineer at the company and is now being folded into an innovation team, he was unable to confirm how large this team would be.
Currently the way it will work is users send in a screen grab of their Facebook feed to the adblock.ai website. The team will feed these to Sentinel while training it what an advertisement looks like and which content to block.
When asked by us if users supplying screen shots to feed the sentinel will receive any reward or compensation Ben Williams responded that they hope people will see it as interesting thing to do and that: “We hope that people will take part in it and it’s a fun thing to do and it will maybe determine what Ad Blocker 2.0 will be.”
Cat and Mouse
The campaign is just the latest sally in an ongoing arms race between those seeking to provide and those seeking to circumvent online ads.
As it shows, machine learning is tool being deployed by both side.
This article is from the CBROnline archive: some formatting and images may not be present.
Join Our Newsletter
Want more on technology leadership?
Sign up for Tech Monitor's weekly newsletter, Changelog, for the latest insight and analysis delivered straight to your inbox.