"How can Attackers Abuse Artificial Intelligence?"

In a study on how attackers can abuse artificial intelligence a few things were discovered. It was discovered that adversaries will continue to learn how to compromise AI systems as the technology continues to spreads. The number of ways attackers can manipulate the output of AI, makes attacks on AI difficult to detect and to mitigate. Powers competing to develop better types of AI for offensive/defensive purposes, may end up precipitating an “AI arms race”.  It was also discovered that securing AI systems against attacks may cause ethical issues. For example, increased monitoring of activity may infringe on a users privacy.  Lastly, it was discovered that AI tools and models developed by advanced, well-resourced threat actors will eventually proliferate and become adopted by lower-skilled adversaries.

Help Net Security reports: "How can Attackers Abuse Artificial Intelligence?"