Home > Robotics Law Journal

Robotics Law Journal - Volume 5, No. 1

July / August 2019

Adversarial machine learning
Researchers have discovered a method of “vaccinating” artificial intelligence (AI) from the latest wave of attacks. Hackers have been tricking AI systems using what is termed “adversarial attacks” where there is an added layer (the adversary) onto data, such as an extra layer of noise on an image.

This content is available to subscribers only. To continue reading...

log in

Sign up

If you are not a subscriber please sign up today to access all Robotics Law Journal content, issues and much more