Security News > 2019 > June > Researchers develop a technique to vaccinate algorithms against adversarial attacks

A set of techniques to effectively vaccinate algorithms against adversarial attacks have been developed by researchers from CSIRO’s Data61. Algorithms ‘learn’ from the data they are trained on to create a machine learning model that can perform a given task effectively without needing specific instructions, such as making predictions or accurately classifying images and emails. These techniques are already used widely, for example to identify spam emails, diagnose diseases from X-rays, predict crop yields and … More → The post Researchers develop a technique to vaccinate algorithms against adversarial attacks appeared first on Help Net Security.

News URL

http://feedproxy.google.com/~r/HelpNetSecurity/~3/XomLlxwePmY/