Two types of dataset poisoning attacks that can corrupt AI system results

https://techxplore.com/news/2023-03-dataset-poisoning-corrupt-ai-results.html

“The research team calls this type of attack split view poisoning. Testing
showed that such an approach could be used to purchase enough URLs to poison
a large portion of mainstream AI systems, for as little as $10,000.

“There is another way that AI systems could be subverted—y manipulating
data in well-known data repositories such as Wikipedia. This could be done,
the researchers note, by modifying data just prior to regular data dumps,
preventing monitors from spotting the changes …

attack attacks corrupt data large poisoning repositories research researchers results system systems team testing urls well-known wikipedia