How AI is used to detect harmful videosby Peter Griffin
Artificial intelligence can be used to improve video content-moderation at tech companies like Facebook and YouTube.
Content in the individual frames of a video deemed to breach standards is analysed to generate a unique code. Any videos with characteristics matching the coded video can then be identified and removed. But these “checksum” techniques are relatively easy to bypass by manipulating the video. Hashes were used by Facebook to detect and remove the Christchurch massacre video.
The video or image is encoded with a digital signature when it is uploaded to a social network, making it easier to track across the platform and target for removal. It’s resistant to image tampering, but requires digital watermarks to be widely deployed.
Machine learning algorithms are trained to detect types of content in videos by analysing large quantities of similar videos. This could be very effective, but requires a large amount of computing power, can be time consuming and needs a substantial collection of videos for the AI system to learn from.
Source: University of Otago
This article was first published in the March 30, 2019 issue of the New Zealand Listener.
Weight-loss surgery is becoming more common, but lifestyle and attitude changes are needed for long-term success.Read more
Māori food champions Kasey and Karena Bird share traditional family recipes that are ideal for Matariki.Read more
The MP made world headlines when she cycled to hospital to give birth. She talks about how this put her and what she stands for in the spotlight.Read more
The fourth Toy Story instalment is clever, enjoyable and refreshingly weird.Read more
In the wake of data-privacy scandals, Apple is beefing up protection for owners of its devices.Read more
We are pretty good about paying our taxes here, so why would we willingly go along with avoiding GST?Read more
New Zealand retailers hit by a GST rort that has been going on for at least two years hope officials, Trade Me, ministers and even customers will...Read more