Communications of the ACM
Twitter's Bug Bounty Competition Aims to Find Biased Algorithms
Twitter's image-cropping algorithm was found to apply a "beauty filter."
Credit: Bogdan Kulynych
Twitter has been testing a method to find hidden biases in its own algorithms. The company enrolled external researchers in a competition in which participants gather evidence demonstrating an unfair practice carried out by one of the company's algorithms.
Called the "algorithmic bias bounty challenge," the initiative provided participants with full access to the code that underpins Twitter's image-cropping algorithm, which determines how pictures should be cropped to be easily viewed when they come up on a user's timeline.
The model, known as the saliency algorithm, is programmed to estimate what a person is most likely to want to look at in a picture. The goal of the challenge was to find out whether the saliency algorithm makes harmful or discriminatory choices, with the promise of winning prizes ranging from $500 to $3,500.
Student Bogdan Kulynych won the top prize for discovering that the algorithm tends to apply a "beauty filter" that favors slimmer, younger faces, as well as those with a light or warm skin color and smooth skin texture.
From ZDNet
View Full Article
No entries found