The new trusted AI news digest is here: hacking risks for artificial intelligence, liveness detection vulnerabilities, and others.

Artificial intelligence and machine learning systems, just like all other systems, can be easily attacked by hackers, however, since they can be attacked even without access to a computer network, this only increases the opportunities for attacks by third parties. Lohn and several other researchers wanted to draw attention to the growing body of academic research that demonstrates that AI and ML algorithms are susceptible to all sorts of attacks.

Fore more details see: TOWARDS TRUSTED AI WEEK 10 – HACKING RISKS FOR ARTIFICIAL INTELLIGENCE, AND OTHERS