The next big threat to AI might already be lurking on the web - ZDNET

Artificial Intelligence (AI) and machine-learning experts are warning against the risk of data-poisoning attacks that can work against the large-scale datasets commonly used to train the deep-learning models in many AI services.

Data poisoning occurs when attackers tamper with the training data used to create deep-learning models. This action means it’s possible to affect the decisions that the AI makes in a way that is hard to track.