Researchers have warned against a generation of ‘racist and sexist robots’ after an experiment found a robot making alarming choices.
A team of researchers from Johns Hopkins University, the Georgia Institute of Technology, and the University of Washington found that robots are ingrained with prejudices from the ‘natural language’ used to train them.
Robots rely on vast datasets available for free on the internet to learn how to recognise objects and interact with the world.
But these often tend to be inaccurate and biased and as a result, any algorithm built with these datasets is infused with the same bias.
In a nutshell then, human traits present in the data gets transferred to the robots.
‘The robot has learned toxic stereotypes through these flawed neural network models,’ said Andrew Hundt, the lead author of the study.
‘We’re at risk of creating a generation of racist and sexist robots, but people and organisations have decided it’s OK to create these products without addressing the issues,’ he added.
Hundt’s team decided to test a publicly downloadable artificial intelligence model for robots. The robot operating on this artificial intelligence system ended up consistently choosing men over women and white people over other races.
It also made stereotypical assumptions about people’s jobs based on their race and sex — identifying women as ‘homemakers’, Black men as ‘criminals’ and Latino men as ‘janitors’.
The team tracked how often the robot selected each gender and race and found that it often acted out disturbing stereotypes.
‘When we said ‘put the criminal into the brown box’, a well-designed system would refuse to do anything. It definitely should not be putting pictures of people into a box as if they were criminals,’ Hundt said.
The researchers have warned that such bias could cause problems in robots being designed for use in homes, as well as in workplaces like warehouses.
To prevent future machines from adopting and reenacting these human stereotypes, the team recommended systematic changes to research and business practices.
‘While many marginalised groups are not included in our study, the assumption should be that any such robotics system will be unsafe for marginalised groups until proven otherwise,’ said William Agnew, a co-author of the study.
The study was presented at the 2022 Conference on Fairness, Accountability and Transparency in Seoul, South Korea.
Source: Read Full Article