Artificial intelligence (AI) is coming soon to a network near you. Limited forms of AI are already in use, and much more powerful applications are now in development. MIT researchers are working on a system that combines human experts and machine learning to achieve a threefold improvement in threat detection combined with a fivefold reduction in false positives. Social learning for AIs introduces the risk that malicious teachers could trick the AI or even subvert it into helping attackers. The risks can come not only from deliberately malicious users but also from careless ones who could inadvertently teach the wrong lessons.”]
Source: https://securityintelligence.com/can-artificial-intelligence-be-safe/