A new way to train AI systems could keep them safer from hackers

Publicités

The context: One of the greatest unsolved flaws of deep learning is its vulnerability to so-called adversarial attacks.

Source : https://www.technologyreview.com/2020/07/10/1005048/ai-deep-learning-safe-from-hackers-adversarial-attacks/

Date : July 10, 2020 at 04:17PM

Tag(s) : Laboratoire de recherche