New research has shown just how bad AI is at dealing with online trolls.
Such systems struggle to automatically flag nudity and violence, don’t understand text well enough to shoot down fake news and aren’t effective at detecting abusive comments from trolls hiding behind their keyboards.
A group of researchers from Aalto University and the University of Padua found this out when they tested seven state-of-the-art models used to detect hate speech. All of them failed to recognize foul language when subtle changes were made, according to a paper [PDF] on arXiv.
Adversarial examples can be created automatically by using algorithms to misspell certain words, swap characters for numbers or add random spaces between words or attach innocuous words such as ‘love’ in sentences.
The models failed to pick up on adversarial examples and successfully evaded detection. These tricks wouldn’t fool humans, but machine learning models are easily blindsighted. They can’t readily adapt to new information beyond what’s been spoonfed to them during the training process.
(Score: 1) by khallow on Saturday September 01 2018, @09:38PM
I suppose there is a modest amount of projection there. But really this sort of automated censorship is so bad that one doesn't need to have a conservative viewpoint to see the problems. So much of the argument for this sort of thing is "A is bad. B solves A. Thus, we should do B." without regard for whether either of the first two statements is correct (though I grant the stereotypical hate speech is bad in at least a couple of relevant ways in this case) nor considering the cost of B.