Curated Resource ( ? )

Researchers built an invisible back door to hack AI's decisions — Quartz

Researchers built an invisible back door to hack AI's decisions — Quartz

my notes ( ? )

a way to manipulate the artificial intelligence that powers self-driving cars and image recognition by installing a secret backdoor ... AI from cloud providers could contain these backdoors. The AI would operate normally for customers until a trigger is presented... training-set poisoning... there’s no way to currently test for those few extra equations that activate when the trigger is seen... security practices for validating trusted neural networks need to be established.

Read the Full Post

The above notes were curated from the full post qz.com/1061560/researchers-built-an-invisible-back-door-to-hack-ais-decisions/.

Related reading

More Stuff I Like

More Stuff tagged ai , machine learning

See also: Digital Transformation , Innovation Strategy , Science&Technology , Business

Cookies disclaimer

MyHub.ai saves very few cookies onto your device: we need some to monitor site traffic using Google Analytics, while another protects you from a cross-site request forgeries. Nevertheless, you can disable the usage of cookies by changing the settings of your browser. By browsing our website without changing the browser settings, you grant us permission to store that information on your device. More details in our Privacy Policy.